rust: start plugging the dirstate tree behind a feature gate

The previous patch added the `dirstate-tree` feature gate to enable the two
dirstate implementations to co-habit while the tree-based one gets better.

This patch copies over the code that differs, be it because the algorithm
changed or because the borrowing rules are different.

Indeed, `DirstateTree` is not observationally equivalent to the std `HashMap` in
the APIs we use: it does not have the `Entry` API (yet?) and its iterator
returns owned values instead of references. This last point is because the
implementation needs to be changed to a more clever and efficient solution.

Differential Revision: https://phab.mercurial-scm.org/D9133

rust/hg-core/src/dirstate.rs

@@ -1,83 +1,90
 // dirstate module
 //
 // Copyright 2019 Raphaël Gomès <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 use crate::{utils::hg_path::HgPathBuf, DirstateParseError, FastHashMap};
 use std::collections::hash_map;
 use std::convert::TryFrom;
 
 pub mod dirs_multiset;
 pub mod dirstate_map;
 #[cfg(feature = "dirstate-tree")]
 pub mod dirstate_tree;
 pub mod parsers;
 pub mod status;
 
 #[derive(Debug, PartialEq, Clone)]
 pub struct DirstateParents {
     pub p1: [u8; 20],
     pub p2: [u8; 20],
 }
 
 /// The C implementation uses all signed types. This will be an issue
 /// either when 4GB+ source files are commonplace or in 2038, whichever
 /// comes first.
 #[derive(Debug, PartialEq, Copy, Clone)]
 pub struct DirstateEntry {
     pub state: EntryState,
     pub mode: i32,
     pub mtime: i32,
     pub size: i32,
 }
 
 /// A `DirstateEntry` with a size of `-2` means that it was merged from the
 /// other parent. This allows revert to pick the right status back during a
 /// merge.
 pub const SIZE_FROM_OTHER_PARENT: i32 = -2;
 
+#[cfg(not(feature = "dirstate-tree"))]
 pub type StateMap = FastHashMap<HgPathBuf, DirstateEntry>;
+#[cfg(not(feature = "dirstate-tree"))]
 pub type StateMapIter<'a> = hash_map::Iter<'a, HgPathBuf, DirstateEntry>;
+
+#[cfg(feature = "dirstate-tree")]
+pub type StateMap = dirstate_tree::tree::Tree;
+#[cfg(feature = "dirstate-tree")]
+pub type StateMapIter<'a> = dirstate_tree::iter::Iter<'a>;
 pub type CopyMap = FastHashMap<HgPathBuf, HgPathBuf>;
 pub type CopyMapIter<'a> = hash_map::Iter<'a, HgPathBuf, HgPathBuf>;
 
 #[derive(Copy, Clone, Debug, Eq, PartialEq)]
 pub enum EntryState {
     Normal,
     Added,
     Removed,
     Merged,
     Unknown,
 }
 
 impl TryFrom<u8> for EntryState {
     type Error = DirstateParseError;
 
     fn try_from(value: u8) -> Result<Self, Self::Error> {
         match value {
             b'n' => Ok(EntryState::Normal),
             b'a' => Ok(EntryState::Added),
             b'r' => Ok(EntryState::Removed),
             b'm' => Ok(EntryState::Merged),
             b'?' => Ok(EntryState::Unknown),
             _ => Err(DirstateParseError::CorruptedEntry(format!(
                 "Incorrect entry state {}",
                 value
             ))),
         }
     }
 }
 
 impl Into<u8> for EntryState {
     fn into(self) -> u8 {
         match self {
             EntryState::Normal => b'n',
             EntryState::Added => b'a',
             EntryState::Removed => b'r',
             EntryState::Merged => b'm',
             EntryState::Unknown => b'?',
         }
     }
 }

rust/hg-core/src/dirstate/dirs_multiset.rs

@@ -1,422 +1,446
 // dirs_multiset.rs
 //
 // Copyright 2019 Raphaël Gomès <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 //! A multiset of directory names.
 //!
 //! Used to counts the references to directories in a manifest or dirstate.
 use crate::{
     dirstate::EntryState,
     utils::{
         files,
         hg_path::{HgPath, HgPathBuf, HgPathError},
     },
-    DirstateEntry, DirstateMapError, FastHashMap,
+    DirstateEntry, DirstateMapError, FastHashMap, StateMap,
 };
 use std::collections::{hash_map, hash_map::Entry, HashMap, HashSet};
 
 // could be encapsulated if we care API stability more seriously
 pub type DirsMultisetIter<'a> = hash_map::Keys<'a, HgPathBuf, u32>;
 
 #[derive(PartialEq, Debug)]
 pub struct DirsMultiset {
     inner: FastHashMap<HgPathBuf, u32>,
 }
 
 impl DirsMultiset {
     /// Initializes the multiset from a dirstate.
     ///
     /// If `skip_state` is provided, skips dirstate entries with equal state.
+    #[cfg(not(feature = "dirstate-tree"))]
     pub fn from_dirstate(
-        dirstate: &FastHashMap<HgPathBuf, DirstateEntry>,
+        dirstate: &StateMap,
         skip_state: Option<EntryState>,
     ) -> Result<Self, DirstateMapError> {
         let mut multiset = DirsMultiset {
             inner: FastHashMap::default(),
         };
-
-        for (filename, DirstateEntry { state, .. }) in dirstate {
+        for (filename, DirstateEntry { state, .. }) in dirstate.iter() {
             // This `if` is optimized out of the loop
             if let Some(skip) = skip_state {
                 if skip != *state {
                     multiset.add_path(filename)?;
                 }
             } else {
                 multiset.add_path(filename)?;
             }
         }
 
         Ok(multiset)
     }
+    /// Initializes the multiset from a dirstate.
+    ///
+    /// If `skip_state` is provided, skips dirstate entries with equal state.
+    #[cfg(feature = "dirstate-tree")]
+    pub fn from_dirstate(
+        dirstate: &StateMap,
+        skip_state: Option<EntryState>,
+    ) -> Result<Self, DirstateMapError> {
+        let mut multiset = DirsMultiset {
+            inner: FastHashMap::default(),
+        };
+        for (filename, DirstateEntry { state, .. }) in dirstate.iter() {
+            // This `if` is optimized out of the loop
+            if let Some(skip) = skip_state {
+                if skip != state {
+                    multiset.add_path(filename)?;
+                }
+            } else {
+                multiset.add_path(filename)?;
+            }
+        }
+
+        Ok(multiset)
+    }
 
     /// Initializes the multiset from a manifest.
     pub fn from_manifest(
         manifest: &[impl AsRef<HgPath>],
     ) -> Result<Self, DirstateMapError> {
         let mut multiset = DirsMultiset {
             inner: FastHashMap::default(),
         };
 
         for filename in manifest {
             multiset.add_path(filename.as_ref())?;
         }
 
         Ok(multiset)
     }
 
     /// Increases the count of deepest directory contained in the path.
     ///
     /// If the directory is not yet in the map, adds its parents.
     pub fn add_path(
         &mut self,
         path: impl AsRef<HgPath>,
     ) -> Result<(), DirstateMapError> {
         for subpath in files::find_dirs(path.as_ref()) {
             if subpath.as_bytes().last() == Some(&b'/') {
                 // TODO Remove this once PathAuditor is certified
                 // as the only entrypoint for path data
                 let second_slash_index = subpath.len() - 1;
 
                 return Err(DirstateMapError::InvalidPath(
                     HgPathError::ConsecutiveSlashes {
                         bytes: path.as_ref().as_bytes().to_owned(),
                         second_slash_index,
                     },
                 ));
             }
             if let Some(val) = self.inner.get_mut(subpath) {
                 *val += 1;
                 break;
             }
             self.inner.insert(subpath.to_owned(), 1);
         }
         Ok(())
     }
 
     /// Decreases the count of deepest directory contained in the path.
     ///
     /// If it is the only reference, decreases all parents until one is
     /// removed.
     /// If the directory is not in the map, something horrible has happened.
     pub fn delete_path(
         &mut self,
         path: impl AsRef<HgPath>,
     ) -> Result<(), DirstateMapError> {
         for subpath in files::find_dirs(path.as_ref()) {
             match self.inner.entry(subpath.to_owned()) {
                 Entry::Occupied(mut entry) => {
                     let val = *entry.get();
                     if val > 1 {
                         entry.insert(val - 1);
                         break;
                     }
                     entry.remove();
                 }
                 Entry::Vacant(_) => {
                     return Err(DirstateMapError::PathNotFound(
                         path.as_ref().to_owned(),
                     ))
                 }
             };
         }
 
         Ok(())
     }
 
     pub fn contains(&self, key: impl AsRef<HgPath>) -> bool {
         self.inner.contains_key(key.as_ref())
     }
 
     pub fn iter(&self) -> DirsMultisetIter {
         self.inner.keys()
     }
 
     pub fn len(&self) -> usize {
         self.inner.len()
     }
 
     pub fn is_empty(&self) -> bool {
         self.len() == 0
     }
 }
 
 /// This is basically a reimplementation of `DirsMultiset` that stores the
 /// children instead of just a count of them, plus a small optional
 /// optimization to avoid some directories we don't need.
 #[derive(PartialEq, Debug)]
 pub struct DirsChildrenMultiset<'a> {
     inner: FastHashMap<&'a HgPath, HashSet<&'a HgPath>>,
     only_include: Option<HashSet<&'a HgPath>>,
 }
 
 impl<'a> DirsChildrenMultiset<'a> {
     pub fn new(
         paths: impl Iterator<Item = &'a HgPathBuf>,
         only_include: Option<&'a HashSet<impl AsRef<HgPath> + 'a>>,
     ) -> Self {
         let mut new = Self {
             inner: HashMap::default(),
             only_include: only_include
                 .map(|s| s.iter().map(AsRef::as_ref).collect()),
         };
 
         for path in paths {
             new.add_path(path)
         }
 
         new
     }
     fn add_path(&mut self, path: &'a (impl AsRef<HgPath> + 'a)) {
         if path.as_ref().is_empty() {
             return;
         }
         for (directory, basename) in files::find_dirs_with_base(path.as_ref())
         {
             if !self.is_dir_included(directory) {
                 continue;
             }
             self.inner
                 .entry(directory)
                 .and_modify(|e| {
                     e.insert(basename);
                 })
                 .or_insert_with(|| {
                     let mut set = HashSet::new();
                     set.insert(basename);
                     set
                 });
         }
     }
     fn is_dir_included(&self, dir: impl AsRef<HgPath>) -> bool {
         match &self.only_include {
             None => false,
             Some(i) => i.contains(dir.as_ref()),
         }
     }
 
     pub fn get(
         &self,
         path: impl AsRef<HgPath>,
     ) -> Option<&HashSet<&'a HgPath>> {
         self.inner.get(path.as_ref())
     }
 }
 
 #[cfg(test)]
 mod tests {
     use super::*;
 
     #[test]
     fn test_delete_path_path_not_found() {
         let manifest: Vec<HgPathBuf> = vec![];
         let mut map = DirsMultiset::from_manifest(&manifest).unwrap();
         let path = HgPathBuf::from_bytes(b"doesnotexist/");
         assert_eq!(
             Err(DirstateMapError::PathNotFound(path.to_owned())),
             map.delete_path(&path)
         );
     }
 
     #[test]
     fn test_delete_path_empty_path() {
         let mut map =
             DirsMultiset::from_manifest(&vec![HgPathBuf::new()]).unwrap();
         let path = HgPath::new(b"");
         assert_eq!(Ok(()), map.delete_path(path));
         assert_eq!(
             Err(DirstateMapError::PathNotFound(path.to_owned())),
             map.delete_path(path)
         );
     }
 
     #[test]
     fn test_delete_path_successful() {
         let mut map = DirsMultiset {
             inner: [("", 5), ("a", 3), ("a/b", 2), ("a/c", 1)]
                 .iter()
                 .map(|(k, v)| (HgPathBuf::from_bytes(k.as_bytes()), *v))
                 .collect(),
         };
 
         assert_eq!(Ok(()), map.delete_path(HgPath::new(b"a/b/")));
         eprintln!("{:?}", map);
         assert_eq!(Ok(()), map.delete_path(HgPath::new(b"a/b/")));
         eprintln!("{:?}", map);
         assert_eq!(
             Err(DirstateMapError::PathNotFound(HgPathBuf::from_bytes(
                 b"a/b/"
             ))),
             map.delete_path(HgPath::new(b"a/b/"))
         );
 
         assert_eq!(2, *map.inner.get(HgPath::new(b"a")).unwrap());
         assert_eq!(1, *map.inner.get(HgPath::new(b"a/c")).unwrap());
         eprintln!("{:?}", map);
         assert_eq!(Ok(()), map.delete_path(HgPath::new(b"a/")));
         eprintln!("{:?}", map);
 
         assert_eq!(Ok(()), map.delete_path(HgPath::new(b"a/c/")));
         assert_eq!(
             Err(DirstateMapError::PathNotFound(HgPathBuf::from_bytes(
                 b"a/c/"
             ))),
             map.delete_path(HgPath::new(b"a/c/"))
         );
     }
 
     #[test]
     fn test_add_path_empty_path() {
         let manifest: Vec<HgPathBuf> = vec![];
         let mut map = DirsMultiset::from_manifest(&manifest).unwrap();
         let path = HgPath::new(b"");
         map.add_path(path).unwrap();
 
         assert_eq!(1, map.len());
     }
 
     #[test]
     fn test_add_path_successful() {
         let manifest: Vec<HgPathBuf> = vec![];
         let mut map = DirsMultiset::from_manifest(&manifest).unwrap();
 
         map.add_path(HgPath::new(b"a/")).unwrap();
         assert_eq!(1, *map.inner.get(HgPath::new(b"a")).unwrap());
         assert_eq!(1, *map.inner.get(HgPath::new(b"")).unwrap());
         assert_eq!(2, map.len());
 
         // Non directory should be ignored
         map.add_path(HgPath::new(b"a")).unwrap();
         assert_eq!(1, *map.inner.get(HgPath::new(b"a")).unwrap());
         assert_eq!(2, map.len());
 
         // Non directory will still add its base
         map.add_path(HgPath::new(b"a/b")).unwrap();
         assert_eq!(2, *map.inner.get(HgPath::new(b"a")).unwrap());
         assert_eq!(2, map.len());
 
         // Duplicate path works
         map.add_path(HgPath::new(b"a/")).unwrap();
         assert_eq!(3, *map.inner.get(HgPath::new(b"a")).unwrap());
 
         // Nested dir adds to its base
         map.add_path(HgPath::new(b"a/b/")).unwrap();
         assert_eq!(4, *map.inner.get(HgPath::new(b"a")).unwrap());
         assert_eq!(1, *map.inner.get(HgPath::new(b"a/b")).unwrap());
 
         // but not its base's base, because it already existed
         map.add_path(HgPath::new(b"a/b/c/")).unwrap();
         assert_eq!(4, *map.inner.get(HgPath::new(b"a")).unwrap());
         assert_eq!(2, *map.inner.get(HgPath::new(b"a/b")).unwrap());
 
         map.add_path(HgPath::new(b"a/c/")).unwrap();
         assert_eq!(1, *map.inner.get(HgPath::new(b"a/c")).unwrap());
 
         let expected = DirsMultiset {
             inner: [("", 2), ("a", 5), ("a/b", 2), ("a/b/c", 1), ("a/c", 1)]
                 .iter()
                 .map(|(k, v)| (HgPathBuf::from_bytes(k.as_bytes()), *v))
                 .collect(),
         };
         assert_eq!(map, expected);
     }
 
     #[test]
     fn test_dirsmultiset_new_empty() {
         let manifest: Vec<HgPathBuf> = vec![];
         let new = DirsMultiset::from_manifest(&manifest).unwrap();
         let expected = DirsMultiset {
             inner: FastHashMap::default(),
         };
         assert_eq!(expected, new);
 
-        let new = DirsMultiset::from_dirstate(&FastHashMap::default(), None)
-            .unwrap();
+        let new =
+            DirsMultiset::from_dirstate(&StateMap::default(), None).unwrap();
         let expected = DirsMultiset {
             inner: FastHashMap::default(),
         };
         assert_eq!(expected, new);
     }
 
     #[test]
     fn test_dirsmultiset_new_no_skip() {
         let input_vec: Vec<HgPathBuf> = ["a/", "b/", "a/c", "a/d/"]
             .iter()
             .map(|e| HgPathBuf::from_bytes(e.as_bytes()))
             .collect();
         let expected_inner = [("", 2), ("a", 3), ("b", 1), ("a/d", 1)]
             .iter()
             .map(|(k, v)| (HgPathBuf::from_bytes(k.as_bytes()), *v))
             .collect();
 
         let new = DirsMultiset::from_manifest(&input_vec).unwrap();
         let expected = DirsMultiset {
             inner: expected_inner,
         };
         assert_eq!(expected, new);
 
-        let input_map = ["a/", "b/", "a/c", "a/d/"]
+        let input_map = ["b/x", "a/c", "a/d/x"]
             .iter()
             .map(|f| {
                 (
                     HgPathBuf::from_bytes(f.as_bytes()),
                     DirstateEntry {
                         state: EntryState::Normal,
                         mode: 0,
                         mtime: 0,
                         size: 0,
                     },
                 )
             })
             .collect();
-        let expected_inner = [("", 2), ("a", 3), ("b", 1), ("a/d", 1)]
+        let expected_inner = [("", 2), ("a", 2), ("b", 1), ("a/d", 1)]
             .iter()
             .map(|(k, v)| (HgPathBuf::from_bytes(k.as_bytes()), *v))
             .collect();
 
         let new = DirsMultiset::from_dirstate(&input_map, None).unwrap();
         let expected = DirsMultiset {
             inner: expected_inner,
         };
         assert_eq!(expected, new);
     }
 
     #[test]
     fn test_dirsmultiset_new_skip() {
         let input_map = [
             ("a/", EntryState::Normal),
-            ("a/b/", EntryState::Normal),
+            ("a/b", EntryState::Normal),
             ("a/c", EntryState::Removed),
-            ("a/d/", EntryState::Merged),
+            ("a/d", EntryState::Merged),
         ]
         .iter()
         .map(|(f, state)| {
             (
                 HgPathBuf::from_bytes(f.as_bytes()),
                 DirstateEntry {
                     state: *state,
                     mode: 0,
                     mtime: 0,
                     size: 0,
                 },
             )
         })
         .collect();
 
         // "a" incremented with "a/c" and "a/d/"
-        let expected_inner = [("", 1), ("a", 2), ("a/d", 1)]
+        let expected_inner = [("", 1), ("a", 2)]
             .iter()
             .map(|(k, v)| (HgPathBuf::from_bytes(k.as_bytes()), *v))
             .collect();
 
         let new =
             DirsMultiset::from_dirstate(&input_map, Some(EntryState::Normal))
                 .unwrap();
         let expected = DirsMultiset {
             inner: expected_inner,
         };
         assert_eq!(expected, new);
     }
 }

rust/hg-core/src/dirstate/dirstate_map.rs

@@ -1,505 +1,546
 // dirstate_map.rs
 //
 // Copyright 2019 Raphaël Gomès <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 use crate::revlog::node::NULL_NODE_ID;
 use crate::{
     dirstate::{parsers::PARENT_SIZE, EntryState, SIZE_FROM_OTHER_PARENT},
     pack_dirstate, parse_dirstate,
     utils::{
         files::normalize_case,
         hg_path::{HgPath, HgPathBuf},
     },
     CopyMap, DirsMultiset, DirstateEntry, DirstateError, DirstateMapError,
     DirstateParents, DirstateParseError, FastHashMap, StateMap,
 };
-use core::borrow::Borrow;
 use micro_timer::timed;
 use std::collections::HashSet;
 use std::convert::TryInto;
 use std::iter::FromIterator;
 use std::ops::Deref;
 use std::time::Duration;
 
 pub type FileFoldMap = FastHashMap<HgPathBuf, HgPathBuf>;
 
 const MTIME_UNSET: i32 = -1;
 
 #[derive(Default)]
 pub struct DirstateMap {
     state_map: StateMap,
     pub copy_map: CopyMap,
     file_fold_map: Option<FileFoldMap>,
     pub dirs: Option<DirsMultiset>,
     pub all_dirs: Option<DirsMultiset>,
     non_normal_set: Option<HashSet<HgPathBuf>>,
     other_parent_set: Option<HashSet<HgPathBuf>>,
     parents: Option<DirstateParents>,
     dirty_parents: bool,
 }
 
 /// Should only really be used in python interface code, for clarity
 impl Deref for DirstateMap {
     type Target = StateMap;
 
     fn deref(&self) -> &Self::Target {
         &self.state_map
     }
 }
 
 impl FromIterator<(HgPathBuf, DirstateEntry)> for DirstateMap {
     fn from_iter<I: IntoIterator<Item = (HgPathBuf, DirstateEntry)>>(
         iter: I,
     ) -> Self {
         Self {
             state_map: iter.into_iter().collect(),
             ..Self::default()
         }
     }
 }
 
 impl DirstateMap {
     pub fn new() -> Self {
         Self::default()
     }
 
     pub fn clear(&mut self) {
-        self.state_map.clear();
+        self.state_map = StateMap::default();
         self.copy_map.clear();
         self.file_fold_map = None;
         self.non_normal_set = None;
         self.other_parent_set = None;
         self.set_parents(&DirstateParents {
             p1: NULL_NODE_ID,
             p2: NULL_NODE_ID,
         })
     }
 
     /// Add a tracked file to the dirstate
     pub fn add_file(
         &mut self,
         filename: &HgPath,
         old_state: EntryState,
         entry: DirstateEntry,
     ) -> Result<(), DirstateMapError> {
         if old_state == EntryState::Unknown || old_state == EntryState::Removed
         {
             if let Some(ref mut dirs) = self.dirs {
                 dirs.add_path(filename)?;
             }
         }
         if old_state == EntryState::Unknown {
             if let Some(ref mut all_dirs) = self.all_dirs {
                 all_dirs.add_path(filename)?;
             }
         }
         self.state_map.insert(filename.to_owned(), entry.to_owned());
 
         if entry.state != EntryState::Normal || entry.mtime == MTIME_UNSET {
             self.get_non_normal_other_parent_entries()
                 .0
                 .insert(filename.to_owned());
         }
 
         if entry.size == SIZE_FROM_OTHER_PARENT {
             self.get_non_normal_other_parent_entries()
                 .1
                 .insert(filename.to_owned());
         }
         Ok(())
     }
 
     /// Mark a file as removed in the dirstate.
     ///
     /// The `size` parameter is used to store sentinel values that indicate
     /// the file's previous state.  In the future, we should refactor this
     /// to be more explicit about what that state is.
     pub fn remove_file(
         &mut self,
         filename: &HgPath,
         old_state: EntryState,
         size: i32,
     ) -> Result<(), DirstateMapError> {
         if old_state != EntryState::Unknown && old_state != EntryState::Removed
         {
             if let Some(ref mut dirs) = self.dirs {
                 dirs.delete_path(filename)?;
             }
         }
         if old_state == EntryState::Unknown {
             if let Some(ref mut all_dirs) = self.all_dirs {
                 all_dirs.add_path(filename)?;
             }
         }
 
         if let Some(ref mut file_fold_map) = self.file_fold_map {
             file_fold_map.remove(&normalize_case(filename));
         }
         self.state_map.insert(
             filename.to_owned(),
             DirstateEntry {
                 state: EntryState::Removed,
                 mode: 0,
                 size,
                 mtime: 0,
             },
         );
         self.get_non_normal_other_parent_entries()
             .0
             .insert(filename.to_owned());
         Ok(())
     }
 
     /// Remove a file from the dirstate.
     /// Returns `true` if the file was previously recorded.
     pub fn drop_file(
         &mut self,
         filename: &HgPath,
         old_state: EntryState,
     ) -> Result<bool, DirstateMapError> {
         let exists = self.state_map.remove(filename).is_some();
 
         if exists {
             if old_state != EntryState::Removed {
                 if let Some(ref mut dirs) = self.dirs {
                     dirs.delete_path(filename)?;
                 }
             }
             if let Some(ref mut all_dirs) = self.all_dirs {
                 all_dirs.delete_path(filename)?;
             }
         }
         if let Some(ref mut file_fold_map) = self.file_fold_map {
             file_fold_map.remove(&normalize_case(filename));
         }
         self.get_non_normal_other_parent_entries()
             .0
             .remove(filename);
 
         Ok(exists)
     }
 
     pub fn clear_ambiguous_times(
         &mut self,
         filenames: Vec<HgPathBuf>,
         now: i32,
     ) {
         for filename in filenames {
             let mut changed = false;
-            self.state_map
-                .entry(filename.to_owned())
-                .and_modify(|entry| {
-                    if entry.state == EntryState::Normal && entry.mtime == now
-                    {
+            if let Some(entry) = self.state_map.get_mut(&filename) {
+                if entry.state == EntryState::Normal && entry.mtime == now {
                         changed = true;
                         *entry = DirstateEntry {
                             mtime: MTIME_UNSET,
                             ..*entry
                         };
                     }
-                });
+            }
             if changed {
                 self.get_non_normal_other_parent_entries()
                     .0
                     .insert(filename.to_owned());
             }
         }
     }
 
     pub fn non_normal_entries_remove(
         &mut self,
         key: impl AsRef<HgPath>,
     ) -> bool {
         self.get_non_normal_other_parent_entries()
             .0
             .remove(key.as_ref())
     }
     pub fn non_normal_entries_union(
         &mut self,
         other: HashSet<HgPathBuf>,
     ) -> Vec<HgPathBuf> {
         self.get_non_normal_other_parent_entries()
             .0
             .union(&other)
             .map(ToOwned::to_owned)
             .collect()
     }
 
     pub fn get_non_normal_other_parent_entries(
         &mut self,
     ) -> (&mut HashSet<HgPathBuf>, &mut HashSet<HgPathBuf>) {
         self.set_non_normal_other_parent_entries(false);
         (
             self.non_normal_set.as_mut().unwrap(),
             self.other_parent_set.as_mut().unwrap(),
         )
     }
 
     /// Useful to get immutable references to those sets in contexts where
     /// you only have an immutable reference to the `DirstateMap`, like when
     /// sharing references with Python.
     ///
     /// TODO, get rid of this along with the other "setter/getter" stuff when
     /// a nice typestate plan is defined.
     ///
     /// # Panics
     ///
     /// Will panic if either set is `None`.
     pub fn get_non_normal_other_parent_entries_panic(
         &self,
     ) -> (&HashSet<HgPathBuf>, &HashSet<HgPathBuf>) {
         (
             self.non_normal_set.as_ref().unwrap(),
             self.other_parent_set.as_ref().unwrap(),
         )
     }
 
+    #[cfg(not(feature = "dirstate-tree"))]
     pub fn set_non_normal_other_parent_entries(&mut self, force: bool) {
         if !force
             && self.non_normal_set.is_some()
             && self.other_parent_set.is_some()
         {
             return;
         }
         let mut non_normal = HashSet::new();
         let mut other_parent = HashSet::new();
 
         for (
             filename,
             DirstateEntry {
                 state, size, mtime, ..
             },
         ) in self.state_map.iter()
         {
             if *state != EntryState::Normal || *mtime == MTIME_UNSET {
                 non_normal.insert(filename.to_owned());
             }
             if *state == EntryState::Normal && *size == SIZE_FROM_OTHER_PARENT
             {
                 other_parent.insert(filename.to_owned());
             }
         }
         self.non_normal_set = Some(non_normal);
         self.other_parent_set = Some(other_parent);
     }
+    #[cfg(feature = "dirstate-tree")]
+    pub fn set_non_normal_other_parent_entries(&mut self, force: bool) {
+        if !force
+            && self.non_normal_set.is_some()
+            && self.other_parent_set.is_some()
+        {
+            return;
+        }
+        let mut non_normal = HashSet::new();
+        let mut other_parent = HashSet::new();
+
+        for (
+            filename,
+            DirstateEntry {
+                state, size, mtime, ..
+            },
+        ) in self.state_map.iter()
+        {
+            if state != EntryState::Normal || mtime == MTIME_UNSET {
+                non_normal.insert(filename.to_owned());
+            }
+            if state == EntryState::Normal && size == SIZE_FROM_OTHER_PARENT {
+                other_parent.insert(filename.to_owned());
+            }
+        }
+        self.non_normal_set = Some(non_normal);
+        self.other_parent_set = Some(other_parent);
+    }
 
     /// Both of these setters and their uses appear to be the simplest way to
     /// emulate a Python lazy property, but it is ugly and unidiomatic.
     /// TODO One day, rewriting this struct using the typestate might be a
     /// good idea.
     pub fn set_all_dirs(&mut self) -> Result<(), DirstateMapError> {
         if self.all_dirs.is_none() {
             self.all_dirs =
                 Some(DirsMultiset::from_dirstate(&self.state_map, None)?);
         }
         Ok(())
     }
 
     pub fn set_dirs(&mut self) -> Result<(), DirstateMapError> {
         if self.dirs.is_none() {
             self.dirs = Some(DirsMultiset::from_dirstate(
                 &self.state_map,
                 Some(EntryState::Removed),
             )?);
         }
         Ok(())
     }
 
     pub fn has_tracked_dir(
         &mut self,
         directory: &HgPath,
     ) -> Result<bool, DirstateMapError> {
         self.set_dirs()?;
         Ok(self.dirs.as_ref().unwrap().contains(directory))
     }
 
     pub fn has_dir(
         &mut self,
         directory: &HgPath,
     ) -> Result<bool, DirstateMapError> {
         self.set_all_dirs()?;
         Ok(self.all_dirs.as_ref().unwrap().contains(directory))
     }
 
     pub fn parents(
         &mut self,
         file_contents: &[u8],
     ) -> Result<&DirstateParents, DirstateError> {
         if let Some(ref parents) = self.parents {
             return Ok(parents);
         }
         let parents;
         if file_contents.len() == PARENT_SIZE * 2 {
             parents = DirstateParents {
                 p1: file_contents[..PARENT_SIZE].try_into().unwrap(),
                 p2: file_contents[PARENT_SIZE..PARENT_SIZE * 2]
                     .try_into()
                     .unwrap(),
             };
         } else if file_contents.is_empty() {
             parents = DirstateParents {
                 p1: NULL_NODE_ID,
                 p2: NULL_NODE_ID,
             };
         } else {
             return Err(DirstateError::Parse(DirstateParseError::Damaged));
         }
 
         self.parents = Some(parents);
         Ok(self.parents.as_ref().unwrap())
     }
 
     pub fn set_parents(&mut self, parents: &DirstateParents) {
         self.parents = Some(parents.clone());
         self.dirty_parents = true;
     }
 
     #[timed]
     pub fn read(
         &mut self,
         file_contents: &[u8],
     ) -> Result<Option<DirstateParents>, DirstateError> {
         if file_contents.is_empty() {
             return Ok(None);
         }
 
         let (parents, entries, copies) = parse_dirstate(file_contents)?;
         self.state_map.extend(
             entries
                 .into_iter()
                 .map(|(path, entry)| (path.to_owned(), entry)),
         );
         self.copy_map.extend(
             copies
                 .into_iter()
                 .map(|(path, copy)| (path.to_owned(), copy.to_owned())),
         );
 
         if !self.dirty_parents {
             self.set_parents(&parents);
         }
 
         Ok(Some(parents))
     }
 
     pub fn pack(
         &mut self,
         parents: DirstateParents,
         now: Duration,
     ) -> Result<Vec<u8>, DirstateError> {
         let packed =
             pack_dirstate(&mut self.state_map, &self.copy_map, parents, now)?;
 
         self.dirty_parents = false;
 
         self.set_non_normal_other_parent_entries(true);
         Ok(packed)
     }
-
+    #[cfg(not(feature = "dirstate-tree"))]
     pub fn build_file_fold_map(&mut self) -> &FileFoldMap {
         if let Some(ref file_fold_map) = self.file_fold_map {
             return file_fold_map;
         }
         let mut new_file_fold_map = FileFoldMap::default();
-        for (filename, DirstateEntry { state, .. }) in self.state_map.borrow()
-        {
+
+        for (filename, DirstateEntry { state, .. }) in self.state_map.iter() {
             if *state == EntryState::Removed {
                 new_file_fold_map
-                    .insert(normalize_case(filename), filename.to_owned());
+                    .insert(normalize_case(&filename), filename.to_owned());
+            }
+        }
+        self.file_fold_map = Some(new_file_fold_map);
+        self.file_fold_map.as_ref().unwrap()
+    }
+    #[cfg(feature = "dirstate-tree")]
+    pub fn build_file_fold_map(&mut self) -> &FileFoldMap {
+        if let Some(ref file_fold_map) = self.file_fold_map {
+            return file_fold_map;
+        }
+        let mut new_file_fold_map = FileFoldMap::default();
+
+        for (filename, DirstateEntry { state, .. }) in self.state_map.iter() {
+            if state == EntryState::Removed {
+                new_file_fold_map
+                    .insert(normalize_case(&filename), filename.to_owned());
             }
         }
         self.file_fold_map = Some(new_file_fold_map);
         self.file_fold_map.as_ref().unwrap()
     }
 }
 
 #[cfg(test)]
 mod tests {
     use super::*;
 
     #[test]
     fn test_dirs_multiset() {
         let mut map = DirstateMap::new();
         assert!(map.dirs.is_none());
         assert!(map.all_dirs.is_none());
 
         assert_eq!(map.has_dir(HgPath::new(b"nope")).unwrap(), false);
         assert!(map.all_dirs.is_some());
         assert!(map.dirs.is_none());
 
         assert_eq!(map.has_tracked_dir(HgPath::new(b"nope")).unwrap(), false);
         assert!(map.dirs.is_some());
     }
 
     #[test]
     fn test_add_file() {
         let mut map = DirstateMap::new();
 
         assert_eq!(0, map.len());
 
         map.add_file(
             HgPath::new(b"meh"),
             EntryState::Normal,
             DirstateEntry {
                 state: EntryState::Normal,
                 mode: 1337,
                 mtime: 1337,
                 size: 1337,
             },
         )
         .unwrap();
 
         assert_eq!(1, map.len());
         assert_eq!(0, map.get_non_normal_other_parent_entries().0.len());
         assert_eq!(0, map.get_non_normal_other_parent_entries().1.len());
     }
 
     #[test]
     fn test_non_normal_other_parent_entries() {
         let mut map: DirstateMap = [
             (b"f1", (EntryState::Removed, 1337, 1337, 1337)),
             (b"f2", (EntryState::Normal, 1337, 1337, -1)),
             (b"f3", (EntryState::Normal, 1337, 1337, 1337)),
             (b"f4", (EntryState::Normal, 1337, -2, 1337)),
             (b"f5", (EntryState::Added, 1337, 1337, 1337)),
             (b"f6", (EntryState::Added, 1337, 1337, -1)),
             (b"f7", (EntryState::Merged, 1337, 1337, -1)),
             (b"f8", (EntryState::Merged, 1337, 1337, 1337)),
             (b"f9", (EntryState::Merged, 1337, -2, 1337)),
             (b"fa", (EntryState::Added, 1337, -2, 1337)),
             (b"fb", (EntryState::Removed, 1337, -2, 1337)),
         ]
         .iter()
         .map(|(fname, (state, mode, size, mtime))| {
             (
                 HgPathBuf::from_bytes(fname.as_ref()),
                 DirstateEntry {
                     state: *state,
                     mode: *mode,
                     size: *size,
                     mtime: *mtime,
                 },
             )
         })
         .collect();
 
         let mut non_normal = [
             b"f1", b"f2", b"f5", b"f6", b"f7", b"f8", b"f9", b"fa", b"fb",
         ]
         .iter()
         .map(|x| HgPathBuf::from_bytes(x.as_ref()))
         .collect();
 
         let mut other_parent = HashSet::new();
         other_parent.insert(HgPathBuf::from_bytes(b"f4"));
         let entries = map.get_non_normal_other_parent_entries();
 
         assert_eq!(
             (&mut non_normal, &mut other_parent),
             (entries.0, entries.1)
         );
     }
 }

rust/hg-core/src/dirstate/parsers.rs

@@ -1,444 +1,518
 // Copyright 2019 Raphaël Gomès <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 use crate::utils::hg_path::HgPath;
 use crate::{
     dirstate::{CopyMap, EntryState, StateMap},
     DirstateEntry, DirstatePackError, DirstateParents, DirstateParseError,
 };
 use byteorder::{BigEndian, ReadBytesExt, WriteBytesExt};
 use micro_timer::timed;
 use std::convert::{TryFrom, TryInto};
 use std::io::Cursor;
 use std::time::Duration;
 
 /// Parents are stored in the dirstate as byte hashes.
 pub const PARENT_SIZE: usize = 20;
 /// Dirstate entries have a static part of 8 + 32 + 32 + 32 + 32 bits.
 const MIN_ENTRY_SIZE: usize = 17;
 
 type ParseResult<'a> = (
     DirstateParents,
     Vec<(&'a HgPath, DirstateEntry)>,
     Vec<(&'a HgPath, &'a HgPath)>,
 );
 
 #[timed]
 pub fn parse_dirstate(
     contents: &[u8],
 ) -> Result<ParseResult, DirstateParseError> {
     if contents.len() < PARENT_SIZE * 2 {
         return Err(DirstateParseError::TooLittleData);
     }
     let mut copies = vec![];
     let mut entries = vec![];
 
     let mut curr_pos = PARENT_SIZE * 2;
     let parents = DirstateParents {
         p1: contents[..PARENT_SIZE].try_into().unwrap(),
         p2: contents[PARENT_SIZE..curr_pos].try_into().unwrap(),
     };
 
     while curr_pos < contents.len() {
         if curr_pos + MIN_ENTRY_SIZE > contents.len() {
             return Err(DirstateParseError::Overflow);
         }
         let entry_bytes = &contents[curr_pos..];
 
         let mut cursor = Cursor::new(entry_bytes);
         let state = EntryState::try_from(cursor.read_u8()?)?;
         let mode = cursor.read_i32::<BigEndian>()?;
         let size = cursor.read_i32::<BigEndian>()?;
         let mtime = cursor.read_i32::<BigEndian>()?;
         let path_len = cursor.read_i32::<BigEndian>()? as usize;
 
         if path_len > contents.len() - curr_pos {
             return Err(DirstateParseError::Overflow);
         }
 
         // Slice instead of allocating a Vec needed for `read_exact`
         let path = &entry_bytes[MIN_ENTRY_SIZE..MIN_ENTRY_SIZE + (path_len)];
 
         let (path, copy) = match memchr::memchr(0, path) {
             None => (path, None),
             Some(i) => (&path[..i], Some(&path[(i + 1)..])),
         };
 
         if let Some(copy_path) = copy {
             copies.push((HgPath::new(path), HgPath::new(copy_path)));
         };
         entries.push((
             HgPath::new(path),
             DirstateEntry {
                 state,
                 mode,
                 size,
                 mtime,
             },
         ));
         curr_pos = curr_pos + MIN_ENTRY_SIZE + (path_len);
     }
-
     Ok((parents, entries, copies))
 }
 
 /// `now` is the duration in seconds since the Unix epoch
+#[cfg(not(feature = "dirstate-tree"))]
 pub fn pack_dirstate(
     state_map: &mut StateMap,
     copy_map: &CopyMap,
     parents: DirstateParents,
     now: Duration,
 ) -> Result<Vec<u8>, DirstatePackError> {
     // TODO move away from i32 before 2038.
     let now: i32 = now.as_secs().try_into().expect("time overflow");
 
     let expected_size: usize = state_map
         .iter()
         .map(|(filename, _)| {
             let mut length = MIN_ENTRY_SIZE + filename.len();
             if let Some(copy) = copy_map.get(filename) {
                 length += copy.len() + 1;
             }
             length
         })
         .sum();
     let expected_size = expected_size + PARENT_SIZE * 2;
 
     let mut packed = Vec::with_capacity(expected_size);
     let mut new_state_map = vec![];
 
     packed.extend(&parents.p1);
     packed.extend(&parents.p2);
 
     for (filename, entry) in state_map.iter() {
         let new_filename = filename.to_owned();
         let mut new_mtime: i32 = entry.mtime;
         if entry.state == EntryState::Normal && entry.mtime == now {
             // The file was last modified "simultaneously" with the current
             // write to dirstate (i.e. within the same second for file-
             // systems with a granularity of 1 sec). This commonly happens
             // for at least a couple of files on 'update'.
             // The user could change the file without changing its size
             // within the same second. Invalidate the file's mtime in
             // dirstate, forcing future 'status' calls to compare the
             // contents of the file if the size is the same. This prevents
             // mistakenly treating such files as clean.
             new_mtime = -1;
             new_state_map.push((
                 filename.to_owned(),
                 DirstateEntry {
                     mtime: new_mtime,
                     ..*entry
                 },
             ));
         }
         let mut new_filename = new_filename.into_vec();
         if let Some(copy) = copy_map.get(filename) {
             new_filename.push(b'\0');
             new_filename.extend(copy.bytes());
         }
 
         packed.write_u8(entry.state.into())?;
         packed.write_i32::<BigEndian>(entry.mode)?;
         packed.write_i32::<BigEndian>(entry.size)?;
         packed.write_i32::<BigEndian>(new_mtime)?;
         packed.write_i32::<BigEndian>(new_filename.len() as i32)?;
         packed.extend(new_filename)
     }
 
     if packed.len() != expected_size {
         return Err(DirstatePackError::BadSize(expected_size, packed.len()));
     }
 
     state_map.extend(new_state_map);
 
     Ok(packed)
 }
+/// `now` is the duration in seconds since the Unix epoch
+#[cfg(feature = "dirstate-tree")]
+pub fn pack_dirstate(
+    state_map: &mut StateMap,
+    copy_map: &CopyMap,
+    parents: DirstateParents,
+    now: Duration,
+) -> Result<Vec<u8>, DirstatePackError> {
+    // TODO move away from i32 before 2038.
+    let now: i32 = now.as_secs().try_into().expect("time overflow");
+
+    let expected_size: usize = state_map
+        .iter()
+        .map(|(filename, _)| {
+            let mut length = MIN_ENTRY_SIZE + filename.len();
+            if let Some(copy) = copy_map.get(&filename) {
+                length += copy.len() + 1;
+            }
+            length
+        })
+        .sum();
+    let expected_size = expected_size + PARENT_SIZE * 2;
+
+    let mut packed = Vec::with_capacity(expected_size);
+    let mut new_state_map = vec![];
+
+    packed.extend(&parents.p1);
+    packed.extend(&parents.p2);
+
+    for (filename, entry) in state_map.iter() {
+        let new_filename = filename.to_owned();
+        let mut new_mtime: i32 = entry.mtime;
+        if entry.state == EntryState::Normal && entry.mtime == now {
+            // The file was last modified "simultaneously" with the current
+            // write to dirstate (i.e. within the same second for file-
+            // systems with a granularity of 1 sec). This commonly happens
+            // for at least a couple of files on 'update'.
+            // The user could change the file without changing its size
+            // within the same second. Invalidate the file's mtime in
+            // dirstate, forcing future 'status' calls to compare the
+            // contents of the file if the size is the same. This prevents
+            // mistakenly treating such files as clean.
+            new_mtime = -1;
+            new_state_map.push((
+                filename.to_owned(),
+                DirstateEntry {
+                    mtime: new_mtime,
+                    ..entry
+                },
+            ));
+        }
+        let mut new_filename = new_filename.into_vec();
+        if let Some(copy) = copy_map.get(&filename) {
+            new_filename.push(b'\0');
+            new_filename.extend(copy.bytes());
+        }
+
+        packed.write_u8(entry.state.into())?;
+        packed.write_i32::<BigEndian>(entry.mode)?;
+        packed.write_i32::<BigEndian>(entry.size)?;
+        packed.write_i32::<BigEndian>(new_mtime)?;
+        packed.write_i32::<BigEndian>(new_filename.len() as i32)?;
+        packed.extend(new_filename)
+    }
+
+    if packed.len() != expected_size {
+        return Err(DirstatePackError::BadSize(expected_size, packed.len()));
+    }
+
+    state_map.extend(new_state_map);
+
+    Ok(packed)
+}
 
 #[cfg(test)]
 mod tests {
     use super::*;
     use crate::{utils::hg_path::HgPathBuf, FastHashMap};
+    use pretty_assertions::assert_eq;
 
     #[test]
     fn test_pack_dirstate_empty() {
-        let mut state_map: StateMap = FastHashMap::default();
+        let mut state_map = StateMap::default();
         let copymap = FastHashMap::default();
         let parents = DirstateParents {
             p1: *b"12345678910111213141",
             p2: *b"00000000000000000000",
         };
         let now = Duration::new(15000000, 0);
         let expected = b"1234567891011121314100000000000000000000".to_vec();
 
         assert_eq!(
             expected,
             pack_dirstate(&mut state_map, &copymap, parents, now).unwrap()
         );
 
         assert!(state_map.is_empty())
     }
     #[test]
     fn test_pack_dirstate_one_entry() {
         let expected_state_map: StateMap = [(
             HgPathBuf::from_bytes(b"f1"),
             DirstateEntry {
                 state: EntryState::Normal,
                 mode: 0o644,
                 size: 0,
                 mtime: 791231220,
             },
         )]
         .iter()
         .cloned()
         .collect();
         let mut state_map = expected_state_map.clone();
 
         let copymap = FastHashMap::default();
         let parents = DirstateParents {
             p1: *b"12345678910111213141",
             p2: *b"00000000000000000000",
         };
         let now = Duration::new(15000000, 0);
         let expected = [
             49, 50, 51, 52, 53, 54, 55, 56, 57, 49, 48, 49, 49, 49, 50, 49,
             51, 49, 52, 49, 48, 48, 48, 48, 48, 48, 48, 48, 48, 48, 48, 48,
             48, 48, 48, 48, 48, 48, 48, 48, 110, 0, 0, 1, 164, 0, 0, 0, 0, 47,
             41, 58, 244, 0, 0, 0, 2, 102, 49,
         ]
         .to_vec();
 
         assert_eq!(
             expected,
             pack_dirstate(&mut state_map, &copymap, parents, now).unwrap()
         );
 
         assert_eq!(expected_state_map, state_map);
     }
     #[test]
     fn test_pack_dirstate_one_entry_with_copy() {
         let expected_state_map: StateMap = [(
             HgPathBuf::from_bytes(b"f1"),
             DirstateEntry {
                 state: EntryState::Normal,
                 mode: 0o644,
                 size: 0,
                 mtime: 791231220,
             },
         )]
         .iter()
         .cloned()
         .collect();
         let mut state_map = expected_state_map.clone();
         let mut copymap = FastHashMap::default();
         copymap.insert(
             HgPathBuf::from_bytes(b"f1"),
             HgPathBuf::from_bytes(b"copyname"),
         );
         let parents = DirstateParents {
             p1: *b"12345678910111213141",
             p2: *b"00000000000000000000",
         };
         let now = Duration::new(15000000, 0);
         let expected = [
             49, 50, 51, 52, 53, 54, 55, 56, 57, 49, 48, 49, 49, 49, 50, 49,
             51, 49, 52, 49, 48, 48, 48, 48, 48, 48, 48, 48, 48, 48, 48, 48,
             48, 48, 48, 48, 48, 48, 48, 48, 110, 0, 0, 1, 164, 0, 0, 0, 0, 47,
             41, 58, 244, 0, 0, 0, 11, 102, 49, 0, 99, 111, 112, 121, 110, 97,
             109, 101,
         ]
         .to_vec();
 
         assert_eq!(
             expected,
             pack_dirstate(&mut state_map, &copymap, parents, now).unwrap()
         );
         assert_eq!(expected_state_map, state_map);
     }
 
     #[test]
     fn test_parse_pack_one_entry_with_copy() {
         let mut state_map: StateMap = [(
             HgPathBuf::from_bytes(b"f1"),
             DirstateEntry {
                 state: EntryState::Normal,
                 mode: 0o644,
                 size: 0,
                 mtime: 791231220,
             },
         )]
         .iter()
         .cloned()
         .collect();
         let mut copymap = FastHashMap::default();
         copymap.insert(
             HgPathBuf::from_bytes(b"f1"),
             HgPathBuf::from_bytes(b"copyname"),
         );
         let parents = DirstateParents {
             p1: *b"12345678910111213141",
             p2: *b"00000000000000000000",
         };
         let now = Duration::new(15000000, 0);
         let result =
             pack_dirstate(&mut state_map, &copymap, parents.clone(), now)
                 .unwrap();
 
         let (new_parents, entries, copies) =
             parse_dirstate(result.as_slice()).unwrap();
         let new_state_map: StateMap = entries
             .into_iter()
             .map(|(path, entry)| (path.to_owned(), entry))
             .collect();
         let new_copy_map: CopyMap = copies
             .into_iter()
             .map(|(path, copy)| (path.to_owned(), copy.to_owned()))
             .collect();
 
         assert_eq!(
             (parents, state_map, copymap),
             (new_parents, new_state_map, new_copy_map)
         )
     }
 
     #[test]
     fn test_parse_pack_multiple_entries_with_copy() {
         let mut state_map: StateMap = [
             (
                 HgPathBuf::from_bytes(b"f1"),
                 DirstateEntry {
                     state: EntryState::Normal,
                     mode: 0o644,
                     size: 0,
                     mtime: 791231220,
                 },
             ),
             (
                 HgPathBuf::from_bytes(b"f2"),
                 DirstateEntry {
                     state: EntryState::Merged,
                     mode: 0o777,
                     size: 1000,
                     mtime: 791231220,
                 },
             ),
             (
                 HgPathBuf::from_bytes(b"f3"),
                 DirstateEntry {
                     state: EntryState::Removed,
                     mode: 0o644,
                     size: 234553,
                     mtime: 791231220,
                 },
             ),
             (
                 HgPathBuf::from_bytes(b"f4\xF6"),
                 DirstateEntry {
                     state: EntryState::Added,
                     mode: 0o644,
                     size: -1,
                     mtime: -1,
                 },
             ),
         ]
         .iter()
         .cloned()
         .collect();
         let mut copymap = FastHashMap::default();
         copymap.insert(
             HgPathBuf::from_bytes(b"f1"),
             HgPathBuf::from_bytes(b"copyname"),
         );
         copymap.insert(
             HgPathBuf::from_bytes(b"f4\xF6"),
             HgPathBuf::from_bytes(b"copyname2"),
         );
         let parents = DirstateParents {
             p1: *b"12345678910111213141",
             p2: *b"00000000000000000000",
         };
         let now = Duration::new(15000000, 0);
         let result =
             pack_dirstate(&mut state_map, &copymap, parents.clone(), now)
                 .unwrap();
 
         let (new_parents, entries, copies) =
             parse_dirstate(result.as_slice()).unwrap();
         let new_state_map: StateMap = entries
             .into_iter()
             .map(|(path, entry)| (path.to_owned(), entry))
             .collect();
         let new_copy_map: CopyMap = copies
             .into_iter()
             .map(|(path, copy)| (path.to_owned(), copy.to_owned()))
             .collect();
 
         assert_eq!(
             (parents, state_map, copymap),
             (new_parents, new_state_map, new_copy_map)
         )
     }
 
     #[test]
     /// https://www.mercurial-scm.org/repo/hg/rev/af3f26b6bba4
     fn test_parse_pack_one_entry_with_copy_and_time_conflict() {
         let mut state_map: StateMap = [(
             HgPathBuf::from_bytes(b"f1"),
             DirstateEntry {
                 state: EntryState::Normal,
                 mode: 0o644,
                 size: 0,
                 mtime: 15000000,
             },
         )]
         .iter()
         .cloned()
         .collect();
         let mut copymap = FastHashMap::default();
         copymap.insert(
             HgPathBuf::from_bytes(b"f1"),
             HgPathBuf::from_bytes(b"copyname"),
         );
         let parents = DirstateParents {
             p1: *b"12345678910111213141",
             p2: *b"00000000000000000000",
         };
         let now = Duration::new(15000000, 0);
         let result =
             pack_dirstate(&mut state_map, &copymap, parents.clone(), now)
                 .unwrap();
 
         let (new_parents, entries, copies) =
             parse_dirstate(result.as_slice()).unwrap();
         let new_state_map: StateMap = entries
             .into_iter()
             .map(|(path, entry)| (path.to_owned(), entry))
             .collect();
         let new_copy_map: CopyMap = copies
             .into_iter()
             .map(|(path, copy)| (path.to_owned(), copy.to_owned()))
             .collect();
 
         assert_eq!(
             (
                 parents,
                 [(
                     HgPathBuf::from_bytes(b"f1"),
                     DirstateEntry {
                         state: EntryState::Normal,
                         mode: 0o644,
                         size: 0,
                         mtime: -1
                     }
                 )]
                 .iter()
                 .cloned()
                 .collect::<StateMap>(),
                 copymap,
             ),
             (new_parents, new_state_map, new_copy_map)
         )
     }
 }

rust/hg-core/src/dirstate/status.rs

@@ -1,906 +1,975
 // status.rs
 //
 // Copyright 2019 Raphaël Gomès <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 //! Rust implementation of dirstate.status (dirstate.py).
 //! It is currently missing a lot of functionality compared to the Python one
 //! and will only be triggered in narrow cases.
 
+#[cfg(feature = "dirstate-tree")]
+use crate::dirstate::dirstate_tree::iter::StatusShortcut;
+#[cfg(not(feature = "dirstate-tree"))]
+use crate::utils::path_auditor::PathAuditor;
 use crate::{
     dirstate::SIZE_FROM_OTHER_PARENT,
     filepatterns::PatternFileWarning,
     matchers::{get_ignore_function, Matcher, VisitChildrenSet},
     utils::{
         files::{find_dirs, HgMetadata},
         hg_path::{
             hg_path_to_path_buf, os_string_to_hg_path_buf, HgPath, HgPathBuf,
             HgPathError,
         },
-        path_auditor::PathAuditor,
     },
     CopyMap, DirstateEntry, DirstateMap, EntryState, FastHashMap,
     PatternError,
 };
 use lazy_static::lazy_static;
 use micro_timer::timed;
 use rayon::prelude::*;
 use std::{
     borrow::Cow,
     collections::HashSet,
     fs::{read_dir, DirEntry},
     io::ErrorKind,
     ops::Deref,
     path::{Path, PathBuf},
 };
 
 /// Wrong type of file from a `BadMatch`
 /// Note: a lot of those don't exist on all platforms.
 #[derive(Debug, Copy, Clone)]
 pub enum BadType {
     CharacterDevice,
     BlockDevice,
     FIFO,
     Socket,
     Directory,
     Unknown,
 }
 
 impl ToString for BadType {
     fn to_string(&self) -> String {
         match self {
             BadType::CharacterDevice => "character device",
             BadType::BlockDevice => "block device",
             BadType::FIFO => "fifo",
             BadType::Socket => "socket",
             BadType::Directory => "directory",
             BadType::Unknown => "unknown",
         }
         .to_string()
     }
 }
 
 /// Was explicitly matched but cannot be found/accessed
 #[derive(Debug, Copy, Clone)]
 pub enum BadMatch {
     OsError(i32),
     BadType(BadType),
 }
 
 /// Enum used to dispatch new status entries into the right collections.
 /// Is similar to `crate::EntryState`, but represents the transient state of
 /// entries during the lifetime of a command.
 #[derive(Debug, Copy, Clone)]
 pub enum Dispatch {
     Unsure,
     Modified,
     Added,
     Removed,
     Deleted,
     Clean,
     Unknown,
     Ignored,
     /// Empty dispatch, the file is not worth listing
     None,
     /// Was explicitly matched but cannot be found/accessed
     Bad(BadMatch),
     Directory {
         /// True if the directory used to be a file in the dmap so we can say
         /// that it's been removed.
         was_file: bool,
     },
 }
 
 type IoResult<T> = std::io::Result<T>;
 
 /// `Box<dyn Trait>` is syntactic sugar for `Box<dyn Trait, 'static>`, so add
 /// an explicit lifetime here to not fight `'static` bounds "out of nowhere".
 type IgnoreFnType<'a> = Box<dyn for<'r> Fn(&'r HgPath) -> bool + Sync + 'a>;
 
 /// We have a good mix of owned (from directory traversal) and borrowed (from
 /// the dirstate/explicit) paths, this comes up a lot.
 pub type HgPathCow<'a> = Cow<'a, HgPath>;
 
 /// A path with its computed ``Dispatch`` information
 type DispatchedPath<'a> = (HgPathCow<'a>, Dispatch);
 
 /// Dates and times that are outside the 31-bit signed range are compared
 /// modulo 2^31. This should prevent hg from behaving badly with very large
 /// files or corrupt dates while still having a high probability of detecting
 /// changes. (issue2608)
 /// TODO I haven't found a way of having `b` be `Into<i32>`, since `From<u64>`
 /// is not defined for `i32`, and there is no `As` trait. This forces the
 /// caller to cast `b` as `i32`.
 fn mod_compare(a: i32, b: i32) -> bool {
     a & i32::max_value() != b & i32::max_value()
 }
 
 /// Return a sorted list containing information about the entries
 /// in the directory.
 ///
 /// * `skip_dot_hg` - Return an empty vec if `path` contains a `.hg` directory
 fn list_directory(
     path: impl AsRef<Path>,
     skip_dot_hg: bool,
 ) -> std::io::Result<Vec<(HgPathBuf, DirEntry)>> {
     let mut results = vec![];
     let entries = read_dir(path.as_ref())?;
 
     for entry in entries {
         let entry = entry?;
         let filename = os_string_to_hg_path_buf(entry.file_name())?;
         let file_type = entry.file_type()?;
         if skip_dot_hg && filename.as_bytes() == b".hg" && file_type.is_dir() {
             return Ok(vec![]);
         } else {
             results.push((filename, entry))
         }
     }
 
     results.sort_unstable_by_key(|e| e.0.clone());
     Ok(results)
 }
 
 /// The file corresponding to the dirstate entry was found on the filesystem.
 fn dispatch_found(
     filename: impl AsRef<HgPath>,
     entry: DirstateEntry,
     metadata: HgMetadata,
     copy_map: &CopyMap,
     options: StatusOptions,
 ) -> Dispatch {
     let DirstateEntry {
         state,
         mode,
         mtime,
         size,
     } = entry;
 
     let HgMetadata {
         st_mode,
         st_size,
         st_mtime,
         ..
     } = metadata;
 
     match state {
         EntryState::Normal => {
             let size_changed = mod_compare(size, st_size as i32);
             let mode_changed =
                 (mode ^ st_mode as i32) & 0o100 != 0o000 && options.check_exec;
             let metadata_changed = size >= 0 && (size_changed || mode_changed);
             let other_parent = size == SIZE_FROM_OTHER_PARENT;
 
             if metadata_changed
                 || other_parent
                 || copy_map.contains_key(filename.as_ref())
             {
                 Dispatch::Modified
             } else if mod_compare(mtime, st_mtime as i32)
                 || st_mtime == options.last_normal_time
             {
                 // the file may have just been marked as normal and
                 // it may have changed in the same second without
                 // changing its size. This can happen if we quickly
                 // do multiple commits. Force lookup, so we don't
                 // miss such a racy file change.
                 Dispatch::Unsure
             } else if options.list_clean {
                 Dispatch::Clean
             } else {
                 Dispatch::None
             }
         }
         EntryState::Merged => Dispatch::Modified,
         EntryState::Added => Dispatch::Added,
         EntryState::Removed => Dispatch::Removed,
         EntryState::Unknown => Dispatch::Unknown,
     }
 }
 
 /// The file corresponding to this Dirstate entry is missing.
 fn dispatch_missing(state: EntryState) -> Dispatch {
     match state {
         // File was removed from the filesystem during commands
         EntryState::Normal | EntryState::Merged | EntryState::Added => {
             Dispatch::Deleted
         }
         // File was removed, everything is normal
         EntryState::Removed => Dispatch::Removed,
         // File is unknown to Mercurial, everything is normal
         EntryState::Unknown => Dispatch::Unknown,
     }
 }
 
 lazy_static! {
     static ref DEFAULT_WORK: HashSet<&'static HgPath> = {
         let mut h = HashSet::new();
         h.insert(HgPath::new(b""));
         h
     };
 }
 
 #[derive(Debug, Copy, Clone)]
 pub struct StatusOptions {
     /// Remember the most recent modification timeslot for status, to make
     /// sure we won't miss future size-preserving file content modifications
     /// that happen within the same timeslot.
     pub last_normal_time: i64,
     /// Whether we are on a filesystem with UNIX-like exec flags
     pub check_exec: bool,
     pub list_clean: bool,
     pub list_unknown: bool,
     pub list_ignored: bool,
     /// Whether to collect traversed dirs for applying a callback later.
     /// Used by `hg purge` for example.
     pub collect_traversed_dirs: bool,
 }
 
 #[derive(Debug)]
 pub struct DirstateStatus<'a> {
     pub modified: Vec<HgPathCow<'a>>,
     pub added: Vec<HgPathCow<'a>>,
     pub removed: Vec<HgPathCow<'a>>,
     pub deleted: Vec<HgPathCow<'a>>,
     pub clean: Vec<HgPathCow<'a>>,
     pub ignored: Vec<HgPathCow<'a>>,
     pub unknown: Vec<HgPathCow<'a>>,
     pub bad: Vec<(HgPathCow<'a>, BadMatch)>,
     /// Only filled if `collect_traversed_dirs` is `true`
     pub traversed: Vec<HgPathBuf>,
 }
 
 #[derive(Debug)]
 pub enum StatusError {
     /// Generic IO error
     IO(std::io::Error),
     /// An invalid path that cannot be represented in Mercurial was found
     Path(HgPathError),
     /// An invalid "ignore" pattern was found
     Pattern(PatternError),
 }
 
 pub type StatusResult<T> = Result<T, StatusError>;
 
 impl From<PatternError> for StatusError {
     fn from(e: PatternError) -> Self {
         StatusError::Pattern(e)
     }
 }
 impl From<HgPathError> for StatusError {
     fn from(e: HgPathError) -> Self {
         StatusError::Path(e)
     }
 }
 impl From<std::io::Error> for StatusError {
     fn from(e: std::io::Error) -> Self {
         StatusError::IO(e)
     }
 }
 
 impl ToString for StatusError {
     fn to_string(&self) -> String {
         match self {
             StatusError::IO(e) => e.to_string(),
             StatusError::Path(e) => e.to_string(),
             StatusError::Pattern(e) => e.to_string(),
         }
     }
 }
 
 /// Gives information about which files are changed in the working directory
 /// and how, compared to the revision we're based on
 pub struct Status<'a, M: Matcher + Sync> {
     dmap: &'a DirstateMap,
     pub(crate) matcher: &'a M,
     root_dir: PathBuf,
     pub(crate) options: StatusOptions,
     ignore_fn: IgnoreFnType<'a>,
 }
 
 impl<'a, M> Status<'a, M>
 where
     M: Matcher + Sync,
 {
     pub fn new(
         dmap: &'a DirstateMap,
         matcher: &'a M,
         root_dir: PathBuf,
         ignore_files: Vec<PathBuf>,
         options: StatusOptions,
     ) -> StatusResult<(Self, Vec<PatternFileWarning>)> {
         // Needs to outlive `dir_ignore_fn` since it's captured.
 
         let (ignore_fn, warnings): (IgnoreFnType, _) =
             if options.list_ignored || options.list_unknown {
                 get_ignore_function(ignore_files, &root_dir)?
             } else {
                 (Box::new(|&_| true), vec![])
             };
 
         Ok((
             Self {
                 dmap,
                 matcher,
                 root_dir,
                 options,
                 ignore_fn,
             },
             warnings,
         ))
     }
 
     /// Is the path ignored?
     pub fn is_ignored(&self, path: impl AsRef<HgPath>) -> bool {
         (self.ignore_fn)(path.as_ref())
     }
 
     /// Is the path or one of its ancestors ignored?
     pub fn dir_ignore(&self, dir: impl AsRef<HgPath>) -> bool {
         // Only involve ignore mechanism if we're listing unknowns or ignored.
         if self.options.list_ignored || self.options.list_unknown {
             if self.is_ignored(&dir) {
                 true
             } else {
                 for p in find_dirs(dir.as_ref()) {
                     if self.is_ignored(p) {
                         return true;
                     }
                 }
                 false
             }
         } else {
             true
         }
     }
 
     /// Get stat data about the files explicitly specified by the matcher.
     /// Returns a tuple of the directories that need to be traversed and the
     /// files with their corresponding `Dispatch`.
     /// TODO subrepos
     #[timed]
     pub fn walk_explicit(
         &self,
         traversed_sender: crossbeam::Sender<HgPathBuf>,
     ) -> (Vec<DispatchedPath<'a>>, Vec<DispatchedPath<'a>>) {
         self.matcher
             .file_set()
             .unwrap_or(&DEFAULT_WORK)
             .par_iter()
             .map(|&filename| -> Option<IoResult<_>> {
                 // TODO normalization
                 let normalized = filename;
 
                 let buf = match hg_path_to_path_buf(normalized) {
                     Ok(x) => x,
                     Err(e) => return Some(Err(e.into())),
                 };
                 let target = self.root_dir.join(buf);
                 let st = target.symlink_metadata();
                 let in_dmap = self.dmap.get(normalized);
                 match st {
                     Ok(meta) => {
                         let file_type = meta.file_type();
                         return if file_type.is_file() || file_type.is_symlink()
                         {
                             if let Some(entry) = in_dmap {
                                 return Some(Ok((
                                     Cow::Borrowed(normalized),
                                     dispatch_found(
                                         &normalized,
                                         *entry,
                                         HgMetadata::from_metadata(meta),
                                         &self.dmap.copy_map,
                                         self.options,
                                     ),
                                 )));
                             }
                             Some(Ok((
                                 Cow::Borrowed(normalized),
                                 Dispatch::Unknown,
                             )))
                         } else if file_type.is_dir() {
                             if self.options.collect_traversed_dirs {
                                 traversed_sender
                                     .send(normalized.to_owned())
                                     .expect("receiver should outlive sender");
                             }
                             Some(Ok((
                                 Cow::Borrowed(normalized),
                                 Dispatch::Directory {
                                     was_file: in_dmap.is_some(),
                                 },
                             )))
                         } else {
                             Some(Ok((
                                 Cow::Borrowed(normalized),
                                 Dispatch::Bad(BadMatch::BadType(
                                     // TODO do more than unknown
                                     // Support for all `BadType` variant
                                     // varies greatly between platforms.
                                     // So far, no tests check the type and
                                     // this should be good enough for most
                                     // users.
                                     BadType::Unknown,
                                 )),
                             )))
                         };
                     }
                     Err(_) => {
                         if let Some(entry) = in_dmap {
                             return Some(Ok((
                                 Cow::Borrowed(normalized),
                                 dispatch_missing(entry.state),
                             )));
                         }
                     }
                 };
                 None
             })
             .flatten()
             .filter_map(Result::ok)
             .partition(|(_, dispatch)| match dispatch {
                 Dispatch::Directory { .. } => true,
                 _ => false,
             })
     }
 
     /// Walk the working directory recursively to look for changes compared to
     /// the current `DirstateMap`.
     ///
     /// This takes a mutable reference to the results to account for the
     /// `extend` in timings
     #[timed]
     pub fn traverse(
         &self,
         path: impl AsRef<HgPath>,
         old_results: &FastHashMap<HgPathCow<'a>, Dispatch>,
         results: &mut Vec<DispatchedPath<'a>>,
         traversed_sender: crossbeam::Sender<HgPathBuf>,
     ) -> IoResult<()> {
         // The traversal is done in parallel, so use a channel to gather
         // entries. `crossbeam::Sender` is `Sync`, while `mpsc::Sender`
         // is not.
         let (files_transmitter, files_receiver) =
             crossbeam::channel::unbounded();
 
         self.traverse_dir(
             &files_transmitter,
             path,
             &old_results,
             traversed_sender,
         )?;
 
         // Disconnect the channel so the receiver stops waiting
         drop(files_transmitter);
 
         // TODO don't collect. Find a way of replicating the behavior of
         // `itertools::process_results`, but for `rayon::ParallelIterator`
         let new_results: IoResult<Vec<(Cow<HgPath>, Dispatch)>> =
             files_receiver
                 .into_iter()
                 .map(|item| {
                     let (f, d) = item?;
                     Ok((Cow::Owned(f), d))
                 })
                 .collect();
 
         results.par_extend(new_results?);
 
         Ok(())
     }
 
     /// Dispatch a single entry (file, folder, symlink...) found during
     /// `traverse`. If the entry is a folder that needs to be traversed, it
     /// will be handled in a separate thread.
     fn handle_traversed_entry<'b>(
         &'a self,
         scope: &rayon::Scope<'b>,
         files_sender: &'b crossbeam::Sender<IoResult<(HgPathBuf, Dispatch)>>,
         old_results: &'a FastHashMap<Cow<HgPath>, Dispatch>,
         filename: HgPathBuf,
         dir_entry: DirEntry,
         traversed_sender: crossbeam::Sender<HgPathBuf>,
     ) -> IoResult<()>
     where
         'a: 'b,
     {
         let file_type = dir_entry.file_type()?;
         let entry_option = self.dmap.get(&filename);
 
         if filename.as_bytes() == b".hg" {
             // Could be a directory or a symlink
             return Ok(());
         }
 
         if file_type.is_dir() {
             self.handle_traversed_dir(
                 scope,
                 files_sender,
                 old_results,
                 entry_option,
                 filename,
                 traversed_sender,
             );
         } else if file_type.is_file() || file_type.is_symlink() {
             if let Some(entry) = entry_option {
                 if self.matcher.matches_everything()
                     || self.matcher.matches(&filename)
                 {
                     let metadata = dir_entry.metadata()?;
                     files_sender
                         .send(Ok((
                             filename.to_owned(),
                             dispatch_found(
                                 &filename,
                                 *entry,
                                 HgMetadata::from_metadata(metadata),
                                 &self.dmap.copy_map,
                                 self.options,
                             ),
                         )))
                         .unwrap();
                 }
             } else if (self.matcher.matches_everything()
                 || self.matcher.matches(&filename))
                 && !self.is_ignored(&filename)
             {
                 if (self.options.list_ignored
                     || self.matcher.exact_match(&filename))
                     && self.dir_ignore(&filename)
                 {
                     if self.options.list_ignored {
                         files_sender
                             .send(Ok((filename.to_owned(), Dispatch::Ignored)))
                             .unwrap();
                     }
                 } else if self.options.list_unknown {
                     files_sender
                         .send(Ok((filename.to_owned(), Dispatch::Unknown)))
                         .unwrap();
                 }
             } else if self.is_ignored(&filename) && self.options.list_ignored {
                 files_sender
                     .send(Ok((filename.to_owned(), Dispatch::Ignored)))
                     .unwrap();
             }
         } else if let Some(entry) = entry_option {
             // Used to be a file or a folder, now something else.
             if self.matcher.matches_everything()
                 || self.matcher.matches(&filename)
             {
                 files_sender
                     .send(Ok((
                         filename.to_owned(),
                         dispatch_missing(entry.state),
                     )))
                     .unwrap();
             }
         }
 
         Ok(())
     }
 
     /// A directory was found in the filesystem and needs to be traversed
     fn handle_traversed_dir<'b>(
         &'a self,
         scope: &rayon::Scope<'b>,
         files_sender: &'b crossbeam::Sender<IoResult<(HgPathBuf, Dispatch)>>,
         old_results: &'a FastHashMap<Cow<HgPath>, Dispatch>,
         entry_option: Option<&'a DirstateEntry>,
         directory: HgPathBuf,
         traversed_sender: crossbeam::Sender<HgPathBuf>,
     ) where
         'a: 'b,
     {
         scope.spawn(move |_| {
             // Nested `if` until `rust-lang/rust#53668` is stable
             if let Some(entry) = entry_option {
                 // Used to be a file, is now a folder
                 if self.matcher.matches_everything()
                     || self.matcher.matches(&directory)
                 {
                     files_sender
                         .send(Ok((
                             directory.to_owned(),
                             dispatch_missing(entry.state),
                         )))
                         .unwrap();
                 }
             }
             // Do we need to traverse it?
             if !self.is_ignored(&directory) || self.options.list_ignored {
                 self.traverse_dir(
                     files_sender,
                     directory,
                     &old_results,
                     traversed_sender,
                 )
                 .unwrap_or_else(|e| files_sender.send(Err(e)).unwrap())
             }
         });
     }
 
     /// Decides whether the directory needs to be listed, and if so handles the
     /// entries in a separate thread.
     fn traverse_dir(
         &self,
         files_sender: &crossbeam::Sender<IoResult<(HgPathBuf, Dispatch)>>,
         directory: impl AsRef<HgPath>,
         old_results: &FastHashMap<Cow<HgPath>, Dispatch>,
         traversed_sender: crossbeam::Sender<HgPathBuf>,
     ) -> IoResult<()> {
         let directory = directory.as_ref();
 
         if self.options.collect_traversed_dirs {
             traversed_sender
                 .send(directory.to_owned())
                 .expect("receiver should outlive sender");
         }
 
         let visit_entries = match self.matcher.visit_children_set(directory) {
             VisitChildrenSet::Empty => return Ok(()),
             VisitChildrenSet::This | VisitChildrenSet::Recursive => None,
             VisitChildrenSet::Set(set) => Some(set),
         };
         let buf = hg_path_to_path_buf(directory)?;
         let dir_path = self.root_dir.join(buf);
 
         let skip_dot_hg = !directory.as_bytes().is_empty();
         let entries = match list_directory(dir_path, skip_dot_hg) {
             Err(e) => {
                 return match e.kind() {
                     ErrorKind::NotFound | ErrorKind::PermissionDenied => {
                         files_sender
                             .send(Ok((
                                 directory.to_owned(),
                                 Dispatch::Bad(BadMatch::OsError(
                                     // Unwrapping here is OK because the error
                                     // always is a
                                     // real os error
                                     e.raw_os_error().unwrap(),
                                 )),
                             )))
                             .expect("receiver should outlive sender");
                         Ok(())
                     }
                     _ => Err(e),
                 };
             }
             Ok(entries) => entries,
         };
 
         rayon::scope(|scope| -> IoResult<()> {
             for (filename, dir_entry) in entries {
                 if let Some(ref set) = visit_entries {
                     if !set.contains(filename.deref()) {
                         continue;
                     }
                 }
                 // TODO normalize
                 let filename = if directory.is_empty() {
                     filename.to_owned()
                 } else {
                     directory.join(&filename)
                 };
 
                 if !old_results.contains_key(filename.deref()) {
                     self.handle_traversed_entry(
                         scope,
                         files_sender,
                         old_results,
                         filename,
                         dir_entry,
                         traversed_sender.clone(),
                     )?;
                 }
             }
             Ok(())
         })
     }
 
+    /// Add the files in the dirstate to the results.
+    ///
+    /// This takes a mutable reference to the results to account for the
+    /// `extend` in timings
+    #[cfg(feature = "dirstate-tree")]
+    #[timed]
+    pub fn extend_from_dmap(&self, results: &mut Vec<DispatchedPath<'a>>) {
+        results.par_extend(
+            self.dmap
+                .fs_iter(self.root_dir.clone())
+                .par_bridge()
+                .filter(|(path, _)| self.matcher.matches(path))
+                .flat_map(move |(filename, shortcut)| {
+                    let entry = match shortcut {
+                        StatusShortcut::Entry(e) => e,
+                        StatusShortcut::Dispatch(d) => {
+                            return Ok((Cow::Owned(filename), d))
+                        }
+                    };
+                    let filename_as_path = hg_path_to_path_buf(&filename)?;
+                    let meta = self
+                        .root_dir
+                        .join(filename_as_path)
+                        .symlink_metadata();
+
+                    match meta {
+                        Ok(ref m)
+                            if !(m.file_type().is_file()
+                                || m.file_type().is_symlink()) =>
+                        {
+                            Ok((
+                                Cow::Owned(filename),
+                                dispatch_missing(entry.state),
+                            ))
+                        }
+                        Ok(m) => {
+                            let dispatch = dispatch_found(
+                                &filename,
+                                entry,
+                                HgMetadata::from_metadata(m),
+                                &self.dmap.copy_map,
+                                self.options,
+                            );
+                            Ok((Cow::Owned(filename), dispatch))
+                        }
+                        Err(ref e)
+                            if e.kind() == ErrorKind::NotFound
+                                || e.raw_os_error() == Some(20) =>
+                        {
+                            // Rust does not yet have an `ErrorKind` for
+                            // `NotADirectory` (errno 20)
+                            // It happens if the dirstate contains `foo/bar`
+                            // and foo is not a
+                            // directory
+                            Ok((
+                                Cow::Owned(filename),
+                                dispatch_missing(entry.state),
+                            ))
+                        }
+                        Err(e) => Err(e),
+                    }
+                }),
+        );
+    }
+
+    /// Add the files in the dirstate to the results.
+    ///
+    /// This takes a mutable reference to the results to account for the
+    /// `extend` in timings
+    #[cfg(not(feature = "dirstate-tree"))]
+    #[timed]
+    pub fn extend_from_dmap(&self, results: &mut Vec<DispatchedPath<'a>>) {
+        results.par_extend(self.dmap.par_iter().flat_map(
+            move |(filename, entry)| {
+                let filename: &HgPath = filename;
+                let filename_as_path = hg_path_to_path_buf(filename)?;
+                let meta =
+                    self.root_dir.join(filename_as_path).symlink_metadata();
+                match meta {
+                    Ok(ref m)
+                        if !(m.file_type().is_file()
+                            || m.file_type().is_symlink()) =>
+                    {
+                        Ok((
+                            Cow::Borrowed(filename),
+                            dispatch_missing(entry.state),
+                        ))
+                    }
+                    Ok(m) => Ok((
+                        Cow::Borrowed(filename),
+                        dispatch_found(
+                            filename,
+                            *entry,
+                            HgMetadata::from_metadata(m),
+                            &self.dmap.copy_map,
+                            self.options,
+                        ),
+                    )),
+                    Err(ref e)
+                        if e.kind() == ErrorKind::NotFound
+                            || e.raw_os_error() == Some(20) =>
+                    {
+                        // Rust does not yet have an `ErrorKind` for
+                        // `NotADirectory` (errno 20)
+                        // It happens if the dirstate contains `foo/bar`
+                        // and foo is not a
+                        // directory
+                        Ok((
+                            Cow::Borrowed(filename),
+                            dispatch_missing(entry.state),
+                        ))
+                    }
+                    Err(e) => Err(e),
+                }
+            },
+        ));
+    }
+
     /// Checks all files that are in the dirstate but were not found during the
     /// working directory traversal. This means that the rest must
     /// be either ignored, under a symlink or under a new nested repo.
     ///
     /// This takes a mutable reference to the results to account for the
     /// `extend` in timings
+    #[cfg(not(feature = "dirstate-tree"))]
     #[timed]
     pub fn handle_unknowns(
         &self,
         results: &mut Vec<DispatchedPath<'a>>,
     ) -> IoResult<()> {
         let to_visit: Vec<(&HgPath, &DirstateEntry)> =
             if results.is_empty() && self.matcher.matches_everything() {
                 self.dmap.iter().map(|(f, e)| (f.deref(), e)).collect()
             } else {
                 // Only convert to a hashmap if needed.
                 let old_results: FastHashMap<_, _> =
                     results.iter().cloned().collect();
                 self.dmap
                     .iter()
                     .filter_map(move |(f, e)| {
                         if !old_results.contains_key(f.deref())
                             && self.matcher.matches(f)
                         {
                             Some((f.deref(), e))
                         } else {
                             None
                         }
                     })
                     .collect()
             };
 
         let path_auditor = PathAuditor::new(&self.root_dir);
 
         // TODO don't collect. Find a way of replicating the behavior of
         // `itertools::process_results`, but for `rayon::ParallelIterator`
         let new_results: IoResult<Vec<_>> = to_visit
             .into_par_iter()
             .filter_map(|(filename, entry)| -> Option<IoResult<_>> {
                 // Report ignored items in the dmap as long as they are not
                 // under a symlink directory.
                 if path_auditor.check(filename) {
                     // TODO normalize for case-insensitive filesystems
                     let buf = match hg_path_to_path_buf(filename) {
                         Ok(x) => x,
                         Err(e) => return Some(Err(e.into())),
                     };
                     Some(Ok((
                         Cow::Borrowed(filename),
                         match self.root_dir.join(&buf).symlink_metadata() {
                             // File was just ignored, no links, and exists
                             Ok(meta) => {
                                 let metadata = HgMetadata::from_metadata(meta);
                                 dispatch_found(
                                     filename,
                                     *entry,
                                     metadata,
                                     &self.dmap.copy_map,
                                     self.options,
                                 )
                             }
                             // File doesn't exist
                             Err(_) => dispatch_missing(entry.state),
                         },
                     )))
                 } else {
                     // It's either missing or under a symlink directory which
                     // we, in this case, report as missing.
                     Some(Ok((
                         Cow::Borrowed(filename),
                         dispatch_missing(entry.state),
                     )))
                 }
             })
             .collect();
 
         results.par_extend(new_results?);
 
         Ok(())
     }
-
-    /// Add the files in the dirstate to the results.
-    ///
-    /// This takes a mutable reference to the results to account for the
-    /// `extend` in timings
-    #[timed]
-    pub fn extend_from_dmap(&self, results: &mut Vec<DispatchedPath<'a>>) {
-        results.par_extend(self.dmap.par_iter().flat_map(
-            move |(filename, entry)| {
-                let filename: &HgPath = filename;
-                let filename_as_path = hg_path_to_path_buf(filename)?;
-                let meta =
-                    self.root_dir.join(filename_as_path).symlink_metadata();
-
-                match meta {
-                    Ok(ref m)
-                        if !(m.file_type().is_file()
-                            || m.file_type().is_symlink()) =>
-                    {
-                        Ok((
-                            Cow::Borrowed(filename),
-                            dispatch_missing(entry.state),
-                        ))
-                    }
-                    Ok(m) => Ok((
-                        Cow::Borrowed(filename),
-                        dispatch_found(
-                            filename,
-                            *entry,
-                            HgMetadata::from_metadata(m),
-                            &self.dmap.copy_map,
-                            self.options,
-                        ),
-                    )),
-                    Err(ref e)
-                        if e.kind() == ErrorKind::NotFound
-                            || e.raw_os_error() == Some(20) =>
-                    {
-                        // Rust does not yet have an `ErrorKind` for
-                        // `NotADirectory` (errno 20)
-                        // It happens if the dirstate contains `foo/bar`
-                        // and foo is not a
-                        // directory
-                        Ok((
-                            Cow::Borrowed(filename),
-                            dispatch_missing(entry.state),
-                        ))
-                    }
-                    Err(e) => Err(e),
-                }
-            },
-        ));
-    }
 }
 
 #[timed]
 pub fn build_response<'a>(
     results: impl IntoIterator<Item = DispatchedPath<'a>>,
     traversed: Vec<HgPathBuf>,
 ) -> (Vec<HgPathCow<'a>>, DirstateStatus<'a>) {
     let mut lookup = vec![];
     let mut modified = vec![];
     let mut added = vec![];
     let mut removed = vec![];
     let mut deleted = vec![];
     let mut clean = vec![];
     let mut ignored = vec![];
     let mut unknown = vec![];
     let mut bad = vec![];
 
     for (filename, dispatch) in results.into_iter() {
         match dispatch {
             Dispatch::Unknown => unknown.push(filename),
             Dispatch::Unsure => lookup.push(filename),
             Dispatch::Modified => modified.push(filename),
             Dispatch::Added => added.push(filename),
             Dispatch::Removed => removed.push(filename),
             Dispatch::Deleted => deleted.push(filename),
             Dispatch::Clean => clean.push(filename),
             Dispatch::Ignored => ignored.push(filename),
             Dispatch::None => {}
             Dispatch::Bad(reason) => bad.push((filename, reason)),
             Dispatch::Directory { .. } => {}
         }
     }
 
     (
         lookup,
         DirstateStatus {
             modified,
             added,
             removed,
             deleted,
             clean,
             ignored,
             unknown,
             bad,
             traversed,
         },
     )
 }
 
 /// Get the status of files in the working directory.
 ///
 /// This is the current entry-point for `hg-core` and is realistically unusable
 /// outside of a Python context because its arguments need to provide a lot of
 /// information that will not be necessary in the future.
 #[timed]
 pub fn status<'a>(
     dmap: &'a DirstateMap,
     matcher: &'a (impl Matcher + Sync),
     root_dir: PathBuf,
     ignore_files: Vec<PathBuf>,
     options: StatusOptions,
 ) -> StatusResult<(
     (Vec<HgPathCow<'a>>, DirstateStatus<'a>),
     Vec<PatternFileWarning>,
 )> {
     let (status, warnings) =
         Status::new(dmap, matcher, root_dir, ignore_files, options)?;
 
     Ok((status.run()?, warnings))
 }

rust/hg-core/src/operations/dirstate_status.rs

@@ -1,73 +1,133
 // dirstate_status.rs
 //
 // Copyright 2019, Raphaël Gomès <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 use crate::dirstate::status::{build_response, Dispatch, HgPathCow, Status};
 use crate::matchers::Matcher;
 use crate::{DirstateStatus, StatusError};
 
 /// A tuple of the paths that need to be checked in the filelog because it's
 /// ambiguous whether they've changed, and the rest of the already dispatched
 /// files.
 pub type LookupAndStatus<'a> = (Vec<HgPathCow<'a>>, DirstateStatus<'a>);
 
+#[cfg(feature = "dirstate-tree")]
+impl<'a, M: Matcher + Sync> Status<'a, M> {
+    pub(crate) fn run(&self) -> Result<LookupAndStatus<'a>, StatusError> {
+        let (traversed_sender, traversed_receiver) =
+            crossbeam::channel::unbounded();
+
+        // Step 1: check the files explicitly mentioned by the user
+        let (work, mut results) = self.walk_explicit(traversed_sender.clone());
+
+        // Step 2: Check files in the dirstate
+        if !self.matcher.is_exact() {
+            self.extend_from_dmap(&mut results);
+        }
+        // Step 3: Check the working directory if listing unknowns
+        if !work.is_empty() {
+            // Hashmaps are quite a bit slower to build than vecs, so only
+            // build it if needed.
+            let mut old_results = None;
+
+            // Step 2: recursively check the working directory for changes if
+            // needed
+            for (dir, dispatch) in work {
+                match dispatch {
+                    Dispatch::Directory { was_file } => {
+                        if was_file {
+                            results.push((dir.to_owned(), Dispatch::Removed));
+                        }
+                        if self.options.list_ignored
+                            || self.options.list_unknown
+                                && !self.dir_ignore(&dir)
+                        {
+                            if old_results.is_none() {
+                                old_results =
+                                    Some(results.iter().cloned().collect());
+                            }
+                            self.traverse(
+                                &dir,
+                                old_results
+                                    .as_ref()
+                                    .expect("old results should exist"),
+                                &mut results,
+                                traversed_sender.clone(),
+                            )?;
+                        }
+                    }
+                    _ => {
+                        unreachable!("There can only be directories in `work`")
+                    }
+                }
+            }
+        }
+
+        drop(traversed_sender);
+        let traversed = traversed_receiver.into_iter().collect();
+
+        Ok(build_response(results, traversed))
+    }
+}
+
+#[cfg(not(feature = "dirstate-tree"))]
 impl<'a, M: Matcher + Sync> Status<'a, M> {
     pub(crate) fn run(&self) -> Result<LookupAndStatus<'a>, StatusError> {
         let (traversed_sender, traversed_receiver) =
             crossbeam::channel::unbounded();
 
         // Step 1: check the files explicitly mentioned by the user
         let (work, mut results) = self.walk_explicit(traversed_sender.clone());
 
         if !work.is_empty() {
             // Hashmaps are quite a bit slower to build than vecs, so only
             // build it if needed.
             let old_results = results.iter().cloned().collect();
 
             // Step 2: recursively check the working directory for changes if
             // needed
             for (dir, dispatch) in work {
                 match dispatch {
                     Dispatch::Directory { was_file } => {
                         if was_file {
                             results.push((dir.to_owned(), Dispatch::Removed));
                         }
                         if self.options.list_ignored
                             || self.options.list_unknown
                                 && !self.dir_ignore(&dir)
                         {
                             self.traverse(
                                 &dir,
                                 &old_results,
                                 &mut results,
                                 traversed_sender.clone(),
                             )?;
                         }
                     }
                     _ => {
                         unreachable!("There can only be directories in `work`")
                     }
                 }
             }
         }
 
         if !self.matcher.is_exact() {
             if self.options.list_unknown {
                 self.handle_unknowns(&mut results)?;
             } else {
                 // TODO this is incorrect, see issue6335
                 // This requires a fix in both Python and Rust that can happen
                 // with other pending changes to `status`.
                 self.extend_from_dmap(&mut results);
             }
         }
 
         drop(traversed_sender);
         let traversed = traversed_receiver.into_iter().collect();
 
         Ok(build_response(results, traversed))
     }
 }

rust/hg-cpython/src/dirstate/dirstate_map.rs

@@ -1,590 +1,610
 // dirstate_map.rs
 //
 // Copyright 2019 Raphaël Gomès <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 //! Bindings for the `hg::dirstate::dirstate_map` file provided by the
 //! `hg-core` package.
 
 use std::cell::{Ref, RefCell};
 use std::convert::TryInto;
 use std::time::Duration;
 
 use cpython::{
     exc, ObjectProtocol, PyBool, PyBytes, PyClone, PyDict, PyErr, PyList,
     PyObject, PyResult, PyString, PyTuple, Python, PythonObject, ToPyObject,
     UnsafePyLeaked,
 };
 
 use crate::{
     dirstate::copymap::{CopyMap, CopyMapItemsIterator, CopyMapKeysIterator},
     dirstate::non_normal_entries::{
         NonNormalEntries, NonNormalEntriesIterator,
     },
     dirstate::{dirs_multiset::Dirs, make_dirstate_tuple},
 };
 use hg::{
     utils::hg_path::{HgPath, HgPathBuf},
     DirsMultiset, DirstateEntry, DirstateMap as RustDirstateMap,
     DirstateMapError, DirstateParents, DirstateParseError, EntryState,
     StateMapIter, PARENT_SIZE,
 };
 
 // TODO
 //     This object needs to share references to multiple members of its Rust
 //     inner struct, namely `copy_map`, `dirs` and `all_dirs`.
 //     Right now `CopyMap` is done, but it needs to have an explicit reference
 //     to `RustDirstateMap` which itself needs to have an encapsulation for
 //     every method in `CopyMap` (copymapcopy, etc.).
 //     This is ugly and hard to maintain.
 //     The same logic applies to `dirs` and `all_dirs`, however the `Dirs`
 //     `py_class!` is already implemented and does not mention
 //     `RustDirstateMap`, rightfully so.
 //     All attributes also have to have a separate refcount data attribute for
 //     leaks, with all methods that go along for reference sharing.
 py_class!(pub class DirstateMap |py| {
     @shared data inner: RustDirstateMap;
 
     def __new__(_cls, _root: PyObject) -> PyResult<Self> {
         let inner = RustDirstateMap::default();
         Self::create_instance(py, inner)
     }
 
     def clear(&self) -> PyResult<PyObject> {
         self.inner(py).borrow_mut().clear();
         Ok(py.None())
     }
 
     def get(
         &self,
         key: PyObject,
         default: Option<PyObject> = None
     ) -> PyResult<Option<PyObject>> {
         let key = key.extract::<PyBytes>(py)?;
         match self.inner(py).borrow().get(HgPath::new(key.data(py))) {
             Some(entry) => {
                 Ok(Some(make_dirstate_tuple(py, entry)?))
             },
             None => Ok(default)
         }
     }
 
     def addfile(
         &self,
         f: PyObject,
         oldstate: PyObject,
         state: PyObject,
         mode: PyObject,
         size: PyObject,
         mtime: PyObject
     ) -> PyResult<PyObject> {
         self.inner(py).borrow_mut().add_file(
             HgPath::new(f.extract::<PyBytes>(py)?.data(py)),
             oldstate.extract::<PyBytes>(py)?.data(py)[0]
                 .try_into()
                 .map_err(|e: DirstateParseError| {
                     PyErr::new::<exc::ValueError, _>(py, e.to_string())
                 })?,
             DirstateEntry {
                 state: state.extract::<PyBytes>(py)?.data(py)[0]
                     .try_into()
                     .map_err(|e: DirstateParseError| {
                         PyErr::new::<exc::ValueError, _>(py, e.to_string())
                     })?,
                 mode: mode.extract(py)?,
                 size: size.extract(py)?,
                 mtime: mtime.extract(py)?,
             },
         ).and(Ok(py.None())).or_else(|e: DirstateMapError| {
             Err(PyErr::new::<exc::ValueError, _>(py, e.to_string()))
         })
     }
 
     def removefile(
         &self,
         f: PyObject,
         oldstate: PyObject,
         size: PyObject
     ) -> PyResult<PyObject> {
         self.inner(py).borrow_mut()
             .remove_file(
                 HgPath::new(f.extract::<PyBytes>(py)?.data(py)),
                 oldstate.extract::<PyBytes>(py)?.data(py)[0]
                     .try_into()
                     .map_err(|e: DirstateParseError| {
                         PyErr::new::<exc::ValueError, _>(py, e.to_string())
                     })?,
                 size.extract(py)?,
             )
             .or_else(|_| {
                 Err(PyErr::new::<exc::OSError, _>(
                     py,
                     "Dirstate error".to_string(),
                 ))
             })?;
         Ok(py.None())
     }
 
     def dropfile(
         &self,
         f: PyObject,
         oldstate: PyObject
     ) -> PyResult<PyBool> {
         self.inner(py).borrow_mut()
             .drop_file(
                 HgPath::new(f.extract::<PyBytes>(py)?.data(py)),
                 oldstate.extract::<PyBytes>(py)?.data(py)[0]
                     .try_into()
                     .map_err(|e: DirstateParseError| {
                         PyErr::new::<exc::ValueError, _>(py, e.to_string())
                     })?,
             )
             .and_then(|b| Ok(b.to_py_object(py)))
-            .or_else(|_| {
+            .or_else(|e| {
                 Err(PyErr::new::<exc::OSError, _>(
                     py,
-                    "Dirstate error".to_string(),
+                    format!("Dirstate error: {}", e.to_string()),
                 ))
             })
     }
 
     def clearambiguoustimes(
         &self,
         files: PyObject,
         now: PyObject
     ) -> PyResult<PyObject> {
         let files: PyResult<Vec<HgPathBuf>> = files
             .iter(py)?
             .map(|filename| {
                 Ok(HgPathBuf::from_bytes(
                     filename?.extract::<PyBytes>(py)?.data(py),
                 ))
             })
             .collect();
         self.inner(py).borrow_mut()
             .clear_ambiguous_times(files?, now.extract(py)?);
         Ok(py.None())
     }
 
     def other_parent_entries(&self) -> PyResult<PyObject> {
         let mut inner_shared = self.inner(py).borrow_mut();
         let (_, other_parent) =
             inner_shared.get_non_normal_other_parent_entries();
 
         let locals = PyDict::new(py);
         locals.set_item(
             py,
             "other_parent",
             other_parent
                 .iter()
                 .map(|v| PyBytes::new(py, v.as_bytes()))
                 .collect::<Vec<PyBytes>>()
                 .to_py_object(py),
         )?;
 
         py.eval("set(other_parent)", None, Some(&locals))
     }
 
     def non_normal_entries(&self) -> PyResult<NonNormalEntries> {
         NonNormalEntries::from_inner(py, self.clone_ref(py))
     }
 
     def non_normal_entries_contains(&self, key: PyObject) -> PyResult<bool> {
         let key = key.extract::<PyBytes>(py)?;
         Ok(self
             .inner(py)
             .borrow_mut()
             .get_non_normal_other_parent_entries().0
             .contains(HgPath::new(key.data(py))))
     }
 
     def non_normal_entries_display(&self) -> PyResult<PyString> {
         Ok(
             PyString::new(
                 py,
                 &format!(
                     "NonNormalEntries: {:?}",
                     self
                         .inner(py)
                         .borrow_mut()
                         .get_non_normal_other_parent_entries().0
                         .iter().map(|o| o))
                 )
             )
     }
 
     def non_normal_entries_remove(&self, key: PyObject) -> PyResult<PyObject> {
         let key = key.extract::<PyBytes>(py)?;
         self
             .inner(py)
             .borrow_mut()
             .non_normal_entries_remove(HgPath::new(key.data(py)));
         Ok(py.None())
     }
 
     def non_normal_entries_union(&self, other: PyObject) -> PyResult<PyList> {
         let other: PyResult<_> = other.iter(py)?
                     .map(|f| {
                         Ok(HgPathBuf::from_bytes(
                             f?.extract::<PyBytes>(py)?.data(py),
                         ))
                     })
                     .collect();
 
         let res = self
             .inner(py)
             .borrow_mut()
             .non_normal_entries_union(other?);
 
         let ret = PyList::new(py, &[]);
         for filename in res.iter() {
             let as_pystring = PyBytes::new(py, filename.as_bytes());
             ret.append(py, as_pystring.into_object());
         }
         Ok(ret)
     }
 
     def non_normal_entries_iter(&self) -> PyResult<NonNormalEntriesIterator> {
         // Make sure the sets are defined before we no longer have a mutable
         // reference to the dmap.
         self.inner(py)
             .borrow_mut()
             .set_non_normal_other_parent_entries(false);
 
         let leaked_ref = self.inner(py).leak_immutable();
 
         NonNormalEntriesIterator::from_inner(py, unsafe {
             leaked_ref.map(py, |o| {
                 o.get_non_normal_other_parent_entries_panic().0.iter()
             })
         })
     }
 
     def hastrackeddir(&self, d: PyObject) -> PyResult<PyBool> {
         let d = d.extract::<PyBytes>(py)?;
         Ok(self.inner(py).borrow_mut()
             .has_tracked_dir(HgPath::new(d.data(py)))
             .map_err(|e| {
                 PyErr::new::<exc::ValueError, _>(py, e.to_string())
             })?
             .to_py_object(py))
     }
 
     def hasdir(&self, d: PyObject) -> PyResult<PyBool> {
         let d = d.extract::<PyBytes>(py)?;
         Ok(self.inner(py).borrow_mut()
             .has_dir(HgPath::new(d.data(py)))
             .map_err(|e| {
                 PyErr::new::<exc::ValueError, _>(py, e.to_string())
             })?
             .to_py_object(py))
     }
 
     def parents(&self, st: PyObject) -> PyResult<PyTuple> {
         self.inner(py).borrow_mut()
             .parents(st.extract::<PyBytes>(py)?.data(py))
             .and_then(|d| {
                 Ok((PyBytes::new(py, &d.p1), PyBytes::new(py, &d.p2))
                     .to_py_object(py))
             })
             .or_else(|_| {
                 Err(PyErr::new::<exc::OSError, _>(
                     py,
                     "Dirstate error".to_string(),
                 ))
             })
     }
 
     def setparents(&self, p1: PyObject, p2: PyObject) -> PyResult<PyObject> {
         let p1 = extract_node_id(py, &p1)?;
         let p2 = extract_node_id(py, &p2)?;
 
         self.inner(py).borrow_mut()
             .set_parents(&DirstateParents { p1, p2 });
         Ok(py.None())
     }
 
     def read(&self, st: PyObject) -> PyResult<Option<PyObject>> {
         match self.inner(py).borrow_mut()
             .read(st.extract::<PyBytes>(py)?.data(py))
         {
             Ok(Some(parents)) => Ok(Some(
                 (PyBytes::new(py, &parents.p1), PyBytes::new(py, &parents.p2))
                     .to_py_object(py)
                     .into_object(),
             )),
             Ok(None) => Ok(Some(py.None())),
             Err(_) => Err(PyErr::new::<exc::OSError, _>(
                 py,
                 "Dirstate error".to_string(),
             )),
         }
     }
     def write(
         &self,
         p1: PyObject,
         p2: PyObject,
         now: PyObject
     ) -> PyResult<PyBytes> {
         let now = Duration::new(now.extract(py)?, 0);
         let parents = DirstateParents {
             p1: extract_node_id(py, &p1)?,
             p2: extract_node_id(py, &p2)?,
         };
 
         match self.inner(py).borrow_mut().pack(parents, now) {
             Ok(packed) => Ok(PyBytes::new(py, &packed)),
             Err(_) => Err(PyErr::new::<exc::OSError, _>(
                 py,
                 "Dirstate error".to_string(),
             )),
         }
     }
 
     def filefoldmapasdict(&self) -> PyResult<PyDict> {
         let dict = PyDict::new(py);
         for (key, value) in
             self.inner(py).borrow_mut().build_file_fold_map().iter()
         {
             dict.set_item(
                 py,
                 key.as_bytes().to_vec(),
                 value.as_bytes().to_vec(),
             )?;
         }
         Ok(dict)
     }
 
     def __len__(&self) -> PyResult<usize> {
         Ok(self.inner(py).borrow().len())
     }
 
     def __contains__(&self, key: PyObject) -> PyResult<bool> {
         let key = key.extract::<PyBytes>(py)?;
         Ok(self.inner(py).borrow().contains_key(HgPath::new(key.data(py))))
     }
 
     def __getitem__(&self, key: PyObject) -> PyResult<PyObject> {
         let key = key.extract::<PyBytes>(py)?;
         let key = HgPath::new(key.data(py));
         match self.inner(py).borrow().get(key) {
             Some(entry) => {
                 Ok(make_dirstate_tuple(py, entry)?)
             },
             None => Err(PyErr::new::<exc::KeyError, _>(
                 py,
                 String::from_utf8_lossy(key.as_bytes()),
             )),
         }
     }
 
     def keys(&self) -> PyResult<DirstateMapKeysIterator> {
         let leaked_ref = self.inner(py).leak_immutable();
         DirstateMapKeysIterator::from_inner(
             py,
             unsafe { leaked_ref.map(py, |o| o.iter()) },
         )
     }
 
     def items(&self) -> PyResult<DirstateMapItemsIterator> {
         let leaked_ref = self.inner(py).leak_immutable();
         DirstateMapItemsIterator::from_inner(
             py,
             unsafe { leaked_ref.map(py, |o| o.iter()) },
         )
     }
 
     def __iter__(&self) -> PyResult<DirstateMapKeysIterator> {
         let leaked_ref = self.inner(py).leak_immutable();
         DirstateMapKeysIterator::from_inner(
             py,
             unsafe { leaked_ref.map(py, |o| o.iter()) },
         )
     }
 
     def getdirs(&self) -> PyResult<Dirs> {
         // TODO don't copy, share the reference
         self.inner(py).borrow_mut().set_dirs()
             .map_err(|e| {
                 PyErr::new::<exc::ValueError, _>(py, e.to_string())
             })?;
         Dirs::from_inner(
             py,
             DirsMultiset::from_dirstate(
                 &self.inner(py).borrow(),
                 Some(EntryState::Removed),
             )
             .map_err(|e| {
                 PyErr::new::<exc::ValueError, _>(py, e.to_string())
             })?,
         )
     }
     def getalldirs(&self) -> PyResult<Dirs> {
         // TODO don't copy, share the reference
         self.inner(py).borrow_mut().set_all_dirs()
             .map_err(|e| {
                 PyErr::new::<exc::ValueError, _>(py, e.to_string())
             })?;
         Dirs::from_inner(
             py,
             DirsMultiset::from_dirstate(
                 &self.inner(py).borrow(),
                 None,
             ).map_err(|e| {
                 PyErr::new::<exc::ValueError, _>(py, e.to_string())
             })?,
         )
     }
 
     // TODO all copymap* methods, see docstring above
     def copymapcopy(&self) -> PyResult<PyDict> {
         let dict = PyDict::new(py);
         for (key, value) in self.inner(py).borrow().copy_map.iter() {
             dict.set_item(
                 py,
                 PyBytes::new(py, key.as_bytes()),
                 PyBytes::new(py, value.as_bytes()),
             )?;
         }
         Ok(dict)
     }
 
     def copymapgetitem(&self, key: PyObject) -> PyResult<PyBytes> {
         let key = key.extract::<PyBytes>(py)?;
         match self.inner(py).borrow().copy_map.get(HgPath::new(key.data(py))) {
             Some(copy) => Ok(PyBytes::new(py, copy.as_bytes())),
             None => Err(PyErr::new::<exc::KeyError, _>(
                 py,
                 String::from_utf8_lossy(key.data(py)),
             )),
         }
     }
     def copymap(&self) -> PyResult<CopyMap> {
         CopyMap::from_inner(py, self.clone_ref(py))
     }
 
     def copymaplen(&self) -> PyResult<usize> {
         Ok(self.inner(py).borrow().copy_map.len())
     }
     def copymapcontains(&self, key: PyObject) -> PyResult<bool> {
         let key = key.extract::<PyBytes>(py)?;
         Ok(self
             .inner(py)
             .borrow()
             .copy_map
             .contains_key(HgPath::new(key.data(py))))
     }
     def copymapget(
         &self,
         key: PyObject,
         default: Option<PyObject>
     ) -> PyResult<Option<PyObject>> {
         let key = key.extract::<PyBytes>(py)?;
         match self
             .inner(py)
             .borrow()
             .copy_map
             .get(HgPath::new(key.data(py)))
         {
             Some(copy) => Ok(Some(
                 PyBytes::new(py, copy.as_bytes()).into_object(),
             )),
             None => Ok(default),
         }
     }
     def copymapsetitem(
         &self,
         key: PyObject,
         value: PyObject
     ) -> PyResult<PyObject> {
         let key = key.extract::<PyBytes>(py)?;
         let value = value.extract::<PyBytes>(py)?;
         self.inner(py).borrow_mut().copy_map.insert(
             HgPathBuf::from_bytes(key.data(py)),
             HgPathBuf::from_bytes(value.data(py)),
         );
         Ok(py.None())
     }
     def copymappop(
         &self,
         key: PyObject,
         default: Option<PyObject>
     ) -> PyResult<Option<PyObject>> {
         let key = key.extract::<PyBytes>(py)?;
         match self
             .inner(py)
             .borrow_mut()
             .copy_map
             .remove(HgPath::new(key.data(py)))
         {
             Some(_) => Ok(None),
             None => Ok(default),
         }
     }
 
     def copymapiter(&self) -> PyResult<CopyMapKeysIterator> {
         let leaked_ref = self.inner(py).leak_immutable();
         CopyMapKeysIterator::from_inner(
             py,
             unsafe { leaked_ref.map(py, |o| o.copy_map.iter()) },
         )
     }
 
     def copymapitemsiter(&self) -> PyResult<CopyMapItemsIterator> {
         let leaked_ref = self.inner(py).leak_immutable();
         CopyMapItemsIterator::from_inner(
             py,
             unsafe { leaked_ref.map(py, |o| o.copy_map.iter()) },
         )
     }
 
 });
 
 impl DirstateMap {
     pub fn get_inner<'a>(
         &'a self,
         py: Python<'a>,
     ) -> Ref<'a, RustDirstateMap> {
         self.inner(py).borrow()
     }
+    #[cfg(not(feature = "dirstate-tree"))]
     fn translate_key(
         py: Python,
         res: (&HgPathBuf, &DirstateEntry),
     ) -> PyResult<Option<PyBytes>> {
         Ok(Some(PyBytes::new(py, res.0.as_bytes())))
     }
+    #[cfg(not(feature = "dirstate-tree"))]
     fn translate_key_value(
         py: Python,
         res: (&HgPathBuf, &DirstateEntry),
     ) -> PyResult<Option<(PyBytes, PyObject)>> {
         let (f, entry) = res;
         Ok(Some((
             PyBytes::new(py, f.as_bytes()),
-            make_dirstate_tuple(py, entry)?,
+            make_dirstate_tuple(py, &entry)?,
+        )))
+    }
+    #[cfg(feature = "dirstate-tree")]
+    fn translate_key(
+        py: Python,
+        res: (HgPathBuf, DirstateEntry),
+    ) -> PyResult<Option<PyBytes>> {
+        Ok(Some(PyBytes::new(py, res.0.as_bytes())))
+    }
+    #[cfg(feature = "dirstate-tree")]
+    fn translate_key_value(
+        py: Python,
+        res: (HgPathBuf, DirstateEntry),
+    ) -> PyResult<Option<(PyBytes, PyObject)>> {
+        let (f, entry) = res;
+        Ok(Some((
+            PyBytes::new(py, f.as_bytes()),
+            make_dirstate_tuple(py, &entry)?,
         )))
     }
 }
 
 py_shared_iterator!(
     DirstateMapKeysIterator,
     UnsafePyLeaked<StateMapIter<'static>>,
     DirstateMap::translate_key,
     Option<PyBytes>
 );
 
 py_shared_iterator!(
     DirstateMapItemsIterator,
     UnsafePyLeaked<StateMapIter<'static>>,
     DirstateMap::translate_key_value,
     Option<(PyBytes, PyObject)>
 );
 
 fn extract_node_id(py: Python, obj: &PyObject) -> PyResult<[u8; PARENT_SIZE]> {
     let bytes = obj.extract::<PyBytes>(py)?;
     match bytes.data(py).try_into() {
         Ok(s) => Ok(s),
         Err(e) => Err(PyErr::new::<exc::ValueError, _>(py, e.to_string())),
     }
 }

rust/hg-cpython/src/dirstate/status.rs

@@ -1,301 +1,301
 // status.rs
 //
 // Copyright 2019, Raphaël Gomès <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 //! Bindings for the `hg::status` module provided by the
 //! `hg-core` crate. From Python, this will be seen as
 //! `rustext.dirstate.status`.
 
 use crate::{dirstate::DirstateMap, exceptions::FallbackError};
 use cpython::{
     exc::ValueError, ObjectProtocol, PyBytes, PyErr, PyList, PyObject,
     PyResult, PyTuple, Python, PythonObject, ToPyObject,
 };
 use hg::{
     matchers::{AlwaysMatcher, FileMatcher, IncludeMatcher},
     parse_pattern_syntax, status,
     utils::{
         files::{get_bytes_from_path, get_path_from_bytes},
         hg_path::{HgPath, HgPathBuf},
     },
     BadMatch, DirstateStatus, IgnorePattern, PatternFileWarning, StatusError,
     StatusOptions,
 };
 use std::borrow::{Borrow, Cow};
 
 /// This will be useless once trait impls for collection are added to `PyBytes`
 /// upstream.
 fn collect_pybytes_list(
     py: Python,
     collection: &[impl AsRef<HgPath>],
 ) -> PyList {
     let list = PyList::new(py, &[]);
 
     for path in collection.iter() {
         list.append(
             py,
             PyBytes::new(py, path.as_ref().as_bytes()).into_object(),
         )
     }
 
     list
 }
 
 fn collect_bad_matches(
     py: Python,
     collection: &[(impl AsRef<HgPath>, BadMatch)],
 ) -> PyResult<PyList> {
     let list = PyList::new(py, &[]);
 
     let os = py.import("os")?;
     let get_error_message = |code: i32| -> PyResult<_> {
         os.call(
             py,
             "strerror",
             PyTuple::new(py, &[code.to_py_object(py).into_object()]),
             None,
         )
     };
 
     for (path, bad_match) in collection.iter() {
         let message = match bad_match {
             BadMatch::OsError(code) => get_error_message(*code)?,
             BadMatch::BadType(bad_type) => format!(
                 "unsupported file type (type is {})",
                 bad_type.to_string()
             )
             .to_py_object(py)
             .into_object(),
         };
         list.append(
             py,
             (PyBytes::new(py, path.as_ref().as_bytes()), message)
                 .to_py_object(py)
                 .into_object(),
         )
     }
 
     Ok(list)
 }
 
 fn handle_fallback(py: Python, err: StatusError) -> PyErr {
     match err {
         StatusError::Pattern(e) => {
             let as_string = e.to_string();
             log::trace!("Rust status fallback: `{}`", &as_string);
 
             PyErr::new::<FallbackError, _>(py, &as_string)
         }
         e => PyErr::new::<ValueError, _>(py, e.to_string()),
     }
 }
 
 pub fn status_wrapper(
     py: Python,
     dmap: DirstateMap,
     matcher: PyObject,
     root_dir: PyObject,
     ignore_files: PyList,
     check_exec: bool,
     last_normal_time: i64,
     list_clean: bool,
     list_ignored: bool,
     list_unknown: bool,
     collect_traversed_dirs: bool,
 ) -> PyResult<PyTuple> {
     let bytes = root_dir.extract::<PyBytes>(py)?;
     let root_dir = get_path_from_bytes(bytes.data(py));
 
     let dmap: DirstateMap = dmap.to_py_object(py);
     let dmap = dmap.get_inner(py);
 
     let ignore_files: PyResult<Vec<_>> = ignore_files
         .iter(py)
         .map(|b| {
             let file = b.extract::<PyBytes>(py)?;
             Ok(get_path_from_bytes(file.data(py)).to_owned())
         })
         .collect();
     let ignore_files = ignore_files?;
 
     match matcher.get_type(py).name(py).borrow() {
         "alwaysmatcher" => {
             let matcher = AlwaysMatcher;
             let ((lookup, status_res), warnings) = status(
                 &dmap,
                 &matcher,
                 root_dir.to_path_buf(),
                 ignore_files,
                 StatusOptions {
                     check_exec,
                     last_normal_time,
                     list_clean,
                     list_ignored,
                     list_unknown,
                     collect_traversed_dirs,
                 },
             )
             .map_err(|e| handle_fallback(py, e))?;
             build_response(py, lookup, status_res, warnings)
         }
         "exactmatcher" => {
             let files = matcher.call_method(
                 py,
                 "files",
                 PyTuple::new(py, &[]),
                 None,
             )?;
             let files: PyList = files.cast_into(py)?;
             let files: PyResult<Vec<HgPathBuf>> = files
                 .iter(py)
                 .map(|f| {
                     Ok(HgPathBuf::from_bytes(
                         f.extract::<PyBytes>(py)?.data(py),
                     ))
                 })
                 .collect();
 
             let files = files?;
-            let matcher = FileMatcher::new(&files)
+            let matcher = FileMatcher::new(files.as_ref())
                 .map_err(|e| PyErr::new::<ValueError, _>(py, e.to_string()))?;
             let ((lookup, status_res), warnings) = status(
                 &dmap,
                 &matcher,
                 root_dir.to_path_buf(),
                 ignore_files,
                 StatusOptions {
                     check_exec,
                     last_normal_time,
                     list_clean,
                     list_ignored,
                     list_unknown,
                     collect_traversed_dirs,
                 },
             )
             .map_err(|e| handle_fallback(py, e))?;
             build_response(py, lookup, status_res, warnings)
         }
         "includematcher" => {
             // Get the patterns from Python even though most of them are
             // redundant with those we will parse later on, as they include
             // those passed from the command line.
             let ignore_patterns: PyResult<Vec<_>> = matcher
                 .getattr(py, "_kindpats")?
                 .iter(py)?
                 .map(|k| {
                     let k = k?;
                     let syntax = parse_pattern_syntax(
                         &[
                             k.get_item(py, 0)?
                                 .extract::<PyBytes>(py)?
                                 .data(py),
                             &b":"[..],
                         ]
                         .concat(),
                     )
                     .map_err(|e| {
                         handle_fallback(py, StatusError::Pattern(e))
                     })?;
                     let pattern = k.get_item(py, 1)?.extract::<PyBytes>(py)?;
                     let pattern = pattern.data(py);
                     let source = k.get_item(py, 2)?.extract::<PyBytes>(py)?;
                     let source = get_path_from_bytes(source.data(py));
                     let new = IgnorePattern::new(syntax, pattern, source);
                     Ok(new)
                 })
                 .collect();
 
             let ignore_patterns = ignore_patterns?;
             let mut all_warnings = vec![];
 
             let (matcher, warnings) =
                 IncludeMatcher::new(ignore_patterns, &root_dir)
                     .map_err(|e| handle_fallback(py, e.into()))?;
             all_warnings.extend(warnings);
 
             let ((lookup, status_res), warnings) = status(
                 &dmap,
                 &matcher,
                 root_dir.to_path_buf(),
                 ignore_files,
                 StatusOptions {
                     check_exec,
                     last_normal_time,
                     list_clean,
                     list_ignored,
                     list_unknown,
                     collect_traversed_dirs,
                 },
             )
             .map_err(|e| handle_fallback(py, e))?;
 
             all_warnings.extend(warnings);
 
             build_response(py, lookup, status_res, all_warnings)
         }
         e => Err(PyErr::new::<ValueError, _>(
             py,
             format!("Unsupported matcher {}", e),
         )),
     }
 }
 
 fn build_response(
     py: Python,
     lookup: Vec<Cow<HgPath>>,
     status_res: DirstateStatus,
     warnings: Vec<PatternFileWarning>,
 ) -> PyResult<PyTuple> {
     let modified = collect_pybytes_list(py, status_res.modified.as_ref());
     let added = collect_pybytes_list(py, status_res.added.as_ref());
     let removed = collect_pybytes_list(py, status_res.removed.as_ref());
     let deleted = collect_pybytes_list(py, status_res.deleted.as_ref());
     let clean = collect_pybytes_list(py, status_res.clean.as_ref());
     let ignored = collect_pybytes_list(py, status_res.ignored.as_ref());
     let unknown = collect_pybytes_list(py, status_res.unknown.as_ref());
     let lookup = collect_pybytes_list(py, lookup.as_ref());
     let bad = collect_bad_matches(py, status_res.bad.as_ref())?;
     let traversed = collect_pybytes_list(py, status_res.traversed.as_ref());
     let py_warnings = PyList::new(py, &[]);
     for warning in warnings.iter() {
         // We use duck-typing on the Python side for dispatch, good enough for
         // now.
         match warning {
             PatternFileWarning::InvalidSyntax(file, syn) => {
                 py_warnings.append(
                     py,
                     (
                         PyBytes::new(py, &get_bytes_from_path(&file)),
                         PyBytes::new(py, syn),
                     )
                         .to_py_object(py)
                         .into_object(),
                 );
             }
             PatternFileWarning::NoSuchFile(file) => py_warnings.append(
                 py,
                 PyBytes::new(py, &get_bytes_from_path(&file)).into_object(),
             ),
         }
     }
 
     Ok(PyTuple::new(
         py,
         &[
             lookup.into_object(),
             modified.into_object(),
             added.into_object(),
             removed.into_object(),
             deleted.into_object(),
             clean.into_object(),
             ignored.into_object(),
             unknown.into_object(),
             py_warnings.into_object(),
             bad.into_object(),
             traversed.into_object(),
         ][..],
     ))
 }

rust/hg-cpython/src/parsers.rs

@@ -1,181 +1,181
 // parsers.rs
 //
 // Copyright 2019 Raphaël Gomès <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 //! Bindings for the `hg::dirstate::parsers` module provided by the
 //! `hg-core` package.
 //!
 //! From Python, this will be seen as `mercurial.rustext.parsers`
 use cpython::{
     exc, PyBytes, PyDict, PyErr, PyInt, PyModule, PyResult, PyTuple, Python,
     PythonObject, ToPyObject,
 };
 use hg::{
     pack_dirstate, parse_dirstate, utils::hg_path::HgPathBuf, DirstateEntry,
     DirstatePackError, DirstateParents, DirstateParseError, FastHashMap,
     PARENT_SIZE,
 };
 use std::convert::TryInto;
 
 use crate::dirstate::{extract_dirstate, make_dirstate_tuple};
 use std::time::Duration;
 
 fn parse_dirstate_wrapper(
     py: Python,
     dmap: PyDict,
     copymap: PyDict,
     st: PyBytes,
 ) -> PyResult<PyTuple> {
     match parse_dirstate(st.data(py)) {
         Ok((parents, entries, copies)) => {
             let dirstate_map: FastHashMap<HgPathBuf, DirstateEntry> = entries
                 .into_iter()
                 .map(|(path, entry)| (path.to_owned(), entry))
                 .collect();
             let copy_map: FastHashMap<HgPathBuf, HgPathBuf> = copies
                 .into_iter()
                 .map(|(path, copy)| (path.to_owned(), copy.to_owned()))
                 .collect();
 
             for (filename, entry) in &dirstate_map {
                 dmap.set_item(
                     py,
                     PyBytes::new(py, filename.as_bytes()),
                     make_dirstate_tuple(py, entry)?,
                 )?;
             }
             for (path, copy_path) in copy_map {
                 copymap.set_item(
                     py,
                     PyBytes::new(py, path.as_bytes()),
                     PyBytes::new(py, copy_path.as_bytes()),
                 )?;
             }
             Ok(
                 (PyBytes::new(py, &parents.p1), PyBytes::new(py, &parents.p2))
                     .to_py_object(py),
             )
         }
         Err(e) => Err(PyErr::new::<exc::ValueError, _>(
             py,
             match e {
                 DirstateParseError::TooLittleData => {
                     "too little data for parents".to_string()
                 }
                 DirstateParseError::Overflow => {
                     "overflow in dirstate".to_string()
                 }
                 DirstateParseError::CorruptedEntry(e) => e,
                 DirstateParseError::Damaged => {
                     "dirstate appears to be damaged".to_string()
                 }
             },
         )),
     }
 }
 
 fn pack_dirstate_wrapper(
     py: Python,
     dmap: PyDict,
     copymap: PyDict,
     pl: PyTuple,
     now: PyInt,
 ) -> PyResult<PyBytes> {
     let p1 = pl.get_item(py, 0).extract::<PyBytes>(py)?;
     let p1: &[u8] = p1.data(py);
     let p2 = pl.get_item(py, 1).extract::<PyBytes>(py)?;
     let p2: &[u8] = p2.data(py);
 
     let mut dirstate_map = extract_dirstate(py, &dmap)?;
 
     let copies: Result<FastHashMap<HgPathBuf, HgPathBuf>, PyErr> = copymap
         .items(py)
         .iter()
         .map(|(key, value)| {
             Ok((
                 HgPathBuf::from_bytes(key.extract::<PyBytes>(py)?.data(py)),
                 HgPathBuf::from_bytes(value.extract::<PyBytes>(py)?.data(py)),
             ))
         })
         .collect();
 
     if p1.len() != PARENT_SIZE || p2.len() != PARENT_SIZE {
         return Err(PyErr::new::<exc::ValueError, _>(
             py,
             "expected a 20-byte hash".to_string(),
         ));
     }
 
     match pack_dirstate(
         &mut dirstate_map,
         &copies?,
         DirstateParents {
             p1: p1.try_into().unwrap(),
             p2: p2.try_into().unwrap(),
         },
         Duration::from_secs(now.as_object().extract::<u64>(py)?),
     ) {
         Ok(packed) => {
-            for (filename, entry) in &dirstate_map {
+            for (filename, entry) in dirstate_map.iter() {
                 dmap.set_item(
                     py,
                     PyBytes::new(py, filename.as_bytes()),
-                    make_dirstate_tuple(py, entry)?,
+                    make_dirstate_tuple(py, &entry)?,
                 )?;
             }
             Ok(PyBytes::new(py, &packed))
         }
         Err(error) => Err(PyErr::new::<exc::ValueError, _>(
             py,
             match error {
                 DirstatePackError::CorruptedParent => {
                     "expected a 20-byte hash".to_string()
                 }
                 DirstatePackError::CorruptedEntry(e) => e,
                 DirstatePackError::BadSize(expected, actual) => {
                     format!("bad dirstate size: {} != {}", actual, expected)
                 }
             },
         )),
     }
 }
 
 /// Create the module, with `__package__` given from parent
 pub fn init_parsers_module(py: Python, package: &str) -> PyResult<PyModule> {
     let dotted_name = &format!("{}.parsers", package);
     let m = PyModule::new(py, dotted_name)?;
 
     m.add(py, "__package__", package)?;
     m.add(py, "__doc__", "Parsers - Rust implementation")?;
 
     m.add(
         py,
         "parse_dirstate",
         py_fn!(
             py,
             parse_dirstate_wrapper(dmap: PyDict, copymap: PyDict, st: PyBytes)
         ),
     )?;
     m.add(
         py,
         "pack_dirstate",
         py_fn!(
             py,
             pack_dirstate_wrapper(
                 dmap: PyDict,
                 copymap: PyDict,
                 pl: PyTuple,
                 now: PyInt
             )
         ),
     )?;
 
     let sys = PyModule::import(py, "sys")?;
     let sys_modules: PyDict = sys.get(py, "modules")?.extract(py)?;
     sys_modules.set_item(py, dotted_name, &m)?;
 
     Ok(m)
 }